INDEX

Explanations

guess the letter

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

The neuron fires strongly on the first significant content word at the start of each new paragraph or section, effectively marking paragraph/section boundaries.

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

duplicated or repeated text segments within documents.

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

regular past-tense verbs ending in "ed".

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

house

0.73

 высо

0.73

льной

0.72

 způsob

0.70

сный

0.70

 bangsa

0.68

種類

0.67

 aswell

0.67

ed

0.67

ferences

0.67

POSITIVE LOGITS

 allegation

0.82

 데이터를

0.82

ВО

0.79

ית

0.79

हां

0.74

➁

0.73

ँग

0.72

 handbag

0.72

 considers

0.72

 প্রত্যা

0.71

Activations Density 0.000%

guess the letter

The neuron fires strongly on the first significant content word at the start of each new paragraph or section, effectively marking paragraph/section boundaries.

duplicated or repeated text segments within documents.

regular past-tense verbs ending in "ed".

No Comments

No Known Activations

guess the letter

The neuron fires strongly on the first significant content word at the start of each new paragraph or section, effectively marking paragraph/section boundaries.

duplicated or repeated text segments within documents.

regular past-tense verbs ending in "ed".

No Comments

No Known Activations