INDEX

Explanations

No common pattern among the provided lists

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

The neuron fires most strongly on content‐bearing descriptive words—especially adjectives and participial verb forms—that carry semantic weight in a sentence.

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

the word "will" followed by "be" or "have" in future tense constructions.

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

auxiliary/modal verb + participle patterns that mark perfect or passive constructions.

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

után

0.77

有多少

0.75

ડા

0.71

endpoints

0.70

your

0.69

 cùng

0.68

hw

0.68

hun

0.68

that

0.67

onate

0.66

POSITIVE LOGITS

ী

0.95

CCION

0.89

愆

0.82

नाडु

0.80

係る

0.79

の新

0.78

сторія

0.78

۔۔

0.77

 tradizionale

0.77

ं

0.76

Activations Density 0.000%

No common pattern among the provided lists

The neuron fires most strongly on content‐bearing descriptive words—especially adjectives and participial verb forms—that carry semantic weight in a sentence.

the word "will" followed by "be" or "have" in future tense constructions.

auxiliary/modal verb + participle patterns that mark perfect or passive constructions.

No Comments

No Known Activations