{"id":29884634,"url":"https://github.com/kempnerinstitute/lueur","last_synced_at":"2025-07-31T15:05:39.000Z","repository":{"id":306878043,"uuid":"1027455357","full_name":"KempnerInstitute/lueur","owner":"KempnerInstitute","description":"👋 A quiet light in the black box,  Lueur is a lightweight framework for Neuro Interpretability.","archived":false,"fork":false,"pushed_at":"2025-07-28T07:01:38.000Z","size":2742,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-28T08:12:54.890Z","etag":null,"topics":["computer-vision","interpretability","neuroscience"],"latest_commit_sha":null,"homepage":"https://KempnerInstitute.github.io/lueur/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/KempnerInstitute.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-07-28T03:28:35.000Z","updated_at":"2025-07-28T07:01:42.000Z","dependencies_parsed_at":"2025-07-28T08:12:59.952Z","dependency_job_id":"7ab1c6e2-4fbc-4dae-84ef-192ee0bf417f","html_url":"https://github.com/KempnerInstitute/lueur","commit_stats":null,"previous_names":["kempnerinstitute/lueur"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/KempnerInstitute/lueur","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KempnerInstitute%2Flueur","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KempnerInstitute%2Flueur/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KempnerInstitute%2Flueur/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KempnerInstitute%2Flueur/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KempnerInstitute","download_url":"https://codeload.github.com/KempnerInstitute/lueur/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KempnerInstitute%2Flueur/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268059993,"owners_count":24188937,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-31T02:00:08.723Z","response_time":66,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","interpretability","neuroscience"],"created_at":"2025-07-31T15:05:30.966Z","updated_at":"2025-07-31T15:05:38.957Z","avatar_url":"https://github.com/KempnerInstitute.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/KempnerInstitute/lueur/blob/main/docs/assets/logo.png?raw=True\" width=\"45%\" alt=\"Lueur logo\" /\u003e\n\u003c/div\u003e\n\n\u003cbr\u003e\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Python-3.10, 3.11, 3.12-efefef\"\u003e\n    \u003cimg alt=\"PyLint\" src=\"https://github.com/KempnerInstitute/lueur/actions/workflows/lint.yml/badge.svg\"\u003e\n    \u003cimg alt=\"Tox\" src=\"https://github.com/KempnerInstitute/lueur/actions/workflows/tox.yml/badge.svg\"\u003e\n    \u003cimg alt=\"Pypi\" src=\"https://github.com/KempnerInstitute/lueur/actions/workflows/publish.yml/badge.svg\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Documentation-Online-EE9D35\"\u003e\n    \u003cimg alt=\"Pepy\" src=\"https://static.pepy.tech/badge/lueur-torch\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/License-MIT-efefef\"\u003e\n\u003c/div\u003e\n\n---\n\n# Lueur\n\n**Lueur** (pronounced *ly.œʁ*) means \"faint glow\" in French. It is a minimal, modular toolbox for NeuroInterpretability.\n\nLueur is intended for researchers interested in understanding representations in artificial neural networks, particularly in contexts inspired by neuroscience. It collects a set of lightweight tools for attribution, feature visualization and concept extraction.\n\nWhile deep networks are not biological systems, their internal structures often raise questions that intersect with those asked in cognitive science and neuroscience. As such models become more capable, it is increasingly important to study not only what they achieve, but how they structure information, and what kinds of functions they implicitly compute.\n\nLueur provides a small, hackable set of tools to aid in that investigation.\n\n## Scope\n\nLueur is built around PyTorch and provides tools for:\n\n- Attribution methods (saliency, integrated gradients, smoothgrads, rise, ...)\n- Feature visualization (fourier, maco, ...)\n- Sparse dictionary learning (SAE variants for concept extraction)\n- Visualization and analysis utilities\n- Tutorials and reproducible interpretability workflows\n\n## Notebooks and Tutorials\n\nThe main companion notebooks and reports are hosted in the following repository:\n[serre-lab/ExplainableNeuro](https://github.com/serre-lab/ExplainableNeuro)\n\n## Installation\n\n```bash\npip install lueur-torch\n```\n\n# 👏 Credits\n\u003cdiv align=\"right\"\u003e\n  \u003cpicture\u003e\n    \u003csource srcset=\"https://kempnerinstitute.harvard.edu/app/uploads/2024/08/Kempner-logo_Full-Color-Kempner-and-Harvard-Logo-Lockup-2048x552.png\"  width=\"60%\" align=\"right\"\u003e\n    \u003cimg  style=\"background-color: rgba(255, 255, 255, 0.8)\" alt=\"Kempner Logo\" src=\"https://kempnerinstitute.harvard.edu/app/uploads/2024/08/Kempner-logo_Full-Color-Kempner-and-Harvard-Logo-Lockup-2048x552.png\" width=\"60%\" align=\"right\"\u003e\n  \u003c/picture\u003e\n\u003c/div\u003e\n\nThis work has been made possible in part by the generous support provided by the Kempner Institute at Harvard University. The institute, established through a gift from the Chan Zuckerberg Initiative Foundation, is dedicated to advancing research in natural and artificial intelligence. The resources and commitment of the Kempner Institute have been instrumental in the development and completion of this project.\n\n\n# Authors\n\n- [Thomas Fel](https://thomasfel.me) - tfel@g.harvard.edu, Kempner Research Fellow, Harvard University.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkempnerinstitute%2Flueur","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkempnerinstitute%2Flueur","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkempnerinstitute%2Flueur/lists"}