INDEX

Explanations

at its core

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

The neuron selectively activates on clause-introducing prepositions or temporal adverbs (e.g. “At,” “In,” “On,” “By,” “From,” “After,” “Under,” “As”) that begin sentences.

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

prepositions that indicate temporal or spatial starting points, particularly "At" and "From" at the beginning of sentences or clauses.

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

sentence-initial prepositions or subordinating function words that introduce temporal or locative adverbial phrases.

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

relation

0.63

 relation

0.63

 analysed

0.52

 epidemiological

0.51

 accordance

0.51

 vitro

0.50

 Relation

0.50

 paramet

0.50

 relação

0.49

मेय

0.49

POSITIVE LOGITS

Together

0.59

Additionally

0.56

While

0.55

 Instead

0.55

 While

0.54

 Within

0.54

此同时

0.54

 Together

0.54

Within

0.54

Offic

0.54

Activations Density 0.275%

at its core

The neuron selectively activates on clause-introducing prepositions or temporal adverbs (e.g. “At,” “In,” “On,” “By,” “From,” “After,” “Under,” “As”) that begin sentences.

prepositions that indicate temporal or spatial starting points, particularly "At" and "From" at the beginning of sentences or clauses.

sentence-initial prepositions or subordinating function words that introduce temporal or locative adverbial phrases.

No Comments

No Known Activations

at its core

The neuron selectively activates on clause-introducing prepositions or temporal adverbs (e.g. “At,” “In,” “On,” “By,” “From,” “After,” “Under,” “As”) that begin sentences.

prepositions that indicate temporal or spatial starting points, particularly "At" and "From" at the beginning of sentences or clauses.

sentence-initial prepositions or subordinating function words that introduce temporal or locative adverbial phrases.

No Comments

No Known Activations