INDEX

Explanations

describing qualities with following nouns

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

The neuron activates on descriptive modifiers—adjectives and adverbs that qualify or intensify nouns (e.g. “best,” “flexible,” “luxurious,” “subpar,” “spacious,” etc.).

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

adjectives describing quality, size, or desirability in descriptive or promotional contexts.

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

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

 nematode

0.80

 monarch

0.73

 ويت

0.71

 energet

0.65

 wetland

0.65

 thermoplastic

0.63

 emergency

0.61

 invertebrate

0.61

 multidiscipl

0.61

箇所

0.61

POSITIVE LOGITS

 semantics

0.73

 skies

0.69

 feelings

0.68

 RATES

0.64

hältnisse

0.64

 wages

0.63

ness

0.63

 했습니다

0.63

férences

0.61

 było

0.61

Activations Density 0.565%

describing qualities with following nouns

The neuron activates on descriptive modifiers—adjectives and adverbs that qualify or intensify nouns (e.g. “best,” “flexible,” “luxurious,” “subpar,” “spacious,” etc.).

adjectives describing quality, size, or desirability in descriptive or promotional contexts.

No Comments

No Known Activations

describing qualities with following nouns

The neuron activates on descriptive modifiers—adjectives and adverbs that qualify or intensify nouns (e.g. “best,” “flexible,” “luxurious,” “subpar,” “spacious,” etc.).

adjectives describing quality, size, or desirability in descriptive or promotional contexts.

No Comments

No Known Activations