# Ablation of a Robot's Brain: Neural Networks Under a Knife

arXiv: https://arxiv.org/abs/1812.05687 · HTML: https://mlsanity.com/paper/1812.05687/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2018.

## Built on by (most cited first, 2 of 2)

- [Fine-grained Interpretation and Causation Analysis in Deep NLP Models](https://mlsanity.com/paper/2105.08039/) (2021)
- [Detection Transformers Under the Knife: A Neuroscience-Inspired Approach to Ablations](https://mlsanity.com/paper/2507.21723/) (2025)

## Abstract (arXiv)

It is still not fully understood exactly how neural networks are able to solve the complex tasks that have recently pushed AI research forward. We present a novel method for determining how information is structured inside a neural network. Using ablation (a neuroscience technique for cutting away parts of a brain to determine their function), we approach several neural network architectures from a biological perspective. Through an analysis of this method's results, we examine important similarities between biological and artificial neural networks to search for the implicit knowledge locked away in the network's weights.