# Exploring Geographic Relative Space in Large Language Models through Activation Patching

arXiv: https://arxiv.org/abs/2605.14535 · HTML: https://mlsanity.com/paper/2605.14535/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge and representations inside LLMs, one of 13 directions in Mechanistic interpretability.
- Builds on 1 of its 9 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- Mechanistic interpretability / [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/)

## Builds on (most cited first, 1 of 1)

- [GIScience in the Era of Artificial Intelligence: A Research Agenda Towards Autonomous GIS](https://mlsanity.com/paper/2503.23633/) (2025)

## Abstract (arXiv)

The increased use of Large Language Models (LLMs) in geography raises substantial questions about the safety of integrating these tools across a wide range of processes and analyses, given our very limited understanding of their inner workings. In this extended abstract, we examine how LLMs process relative geographic space using activation patching, an emerging tool for mechanistic interpretability.