# A Case Study on Concept Induction for Neuron-Level Interpretability in CNN

arXiv: https://arxiv.org/abs/2603.00197 · HTML: https://mlsanity.com/paper/2603.00197/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 5 of 5)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Efficient Concept Induction for Description Logics](https://mlsanity.com/paper/1812.03243/) (2018)
- [On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis](https://mlsanity.com/paper/2404.13567/) (2024)

## Built on by (most cited first, 1 of 1)

- [Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis](https://mlsanity.com/paper/2608.14729/) (2026)

## Abstract (arXiv)

Deep Neural Networks (DNNs) have advanced applications in domains such as healthcare, autonomous systems, and scene understanding, yet the internal semantics of their hidden neurons remain poorly understood. Prior work introduced a Concept Induction-based framework for hidden neuron analysis and demonstrated its effectiveness on the ADE20K dataset. In this case study, we investigate whether the approach generalizes by applying it to the SUN2012 dataset, a large-scale scene recognition benchmark. Using the same workflow, we assign interpretable semantic labels to neurons and validate them through web-sourced images and statistical testing. Our findings confirm that the method transfers to SUN2012, showing its broader applicability.