INDEX

Explanations

options or choices

np_acts-logits-general · gemini-2.5-flash-lite

The neuron fires on expressions that describe spatial proximity, access, or how easily a place or feature can be reached (e.g. “easy access to…,” “walking distance to…,” “located … drive,” etc.).

oai_token-act-pair · o4-mini Triggered by @jyhe0408

phrases describing convenience or ease of access to locations.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

descriptions of accessibility and proximity, highlighting locations that are easy to reach, close by, or conveniently connected.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 незакон

0.78

 મત

0.74

PROXY

0.73

 തന്റെ

0.72

INDUST

0.72

 якобы

0.70

 unlawfully

0.68

 নির্মম

0.67

 своє

0.65

 অবিলম্বে

0.64

POSITIVE LOGITS

 easily

0.92

 plenty

0.85

 hilly

0.82

 manageable

0.80

if

0.79

 breezes

0.76

 chilly