INDEX

Explanations

information about

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

The neuron detects mentions of an “account” or detailed report/description in the text.

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

the phrase "detailed account" or similar phrases combining "detailed" with descriptive nouns.

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

mentions of detailed, authoritative accounts or descriptions, such as an in-depth look, statement, evidence, or views on a subject.

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

が発生

0.65

ご連絡

0.62

 mieć

0.60

パターン

0.60

 singolo

0.59

ス

0.57

 NONCLUSTERED

0.56

場合は

0.55

 dział

0.55

 Alumin

0.54

POSITIVE LOGITS

of

1.11

 about

1.05

关于

0.95

 về

0.89

關於

0.88

 tentang

0.86

about

0.83

 ofthe

0.82

 अबाउट

0.81

 apie

0.81

Activations Density 0.000%

information about

The neuron detects mentions of an “account” or detailed report/description in the text.

the phrase "detailed account" or similar phrases combining "detailed" with descriptive nouns.

mentions of detailed, authoritative accounts or descriptions, such as an in-depth look, statement, evidence, or views on a subject.

No Comments

No Known Activations

information about

The neuron detects mentions of an “account” or detailed report/description in the text.

the phrase "detailed account" or similar phrases combining "detailed" with descriptive nouns.

mentions of detailed, authoritative accounts or descriptions, such as an in-depth look, statement, evidence, or views on a subject.

No Comments

No Known Activations