awesome_deep_learning_interpretability

Why we included this project

Model interpretability is a sprawling field, and this list does the sorting for you. It collects high-citation and top-conference papers on explaining neural networks, from visual methods like class activation maps and concept-based approaches to uncertainty evaluation and causal explanations. Each row links the paper and, when the authors published one, the code, so you can go from reading a method to running it. The table is organized by year and venue, with a separate citation-sorted view for finding the most influential work first. It also bundles 159 paper PDFs in a cloud folder, which helps when a paywall gets in the way. This is a research reference rather than a tool you deploy, but for anyone building or auditing explainable systems it saves a lot of literature hunting.