INDEX

Explanations

little/bit more

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

The neuron consistently lights up on words that express degree or amount—comparatives, diminutives, and similar modifiers (e.g. “little,” “longer,” “better”).

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

the phrase "a little" followed by an adjective or adverb.

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

expressions that hedge or downplay magnitude by indicating a small or slight degree.

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

 Furious

1.06

 πολλά

0.97

قية

0.96

পদ

0.96

পদে

0.96

 وعند

0.93

 muitas

0.92

 них

0.91

ança

0.90

عاد

0.90

POSITIVE LOGITS

씩

1.40

ずつ

1.14

1.11

หน่อย

1.04

🤏

1.02

 inconvenience

1.01

খানি

1.01

mbox

1.00

0.96

Activations Density 0.096%

little/bit more

The neuron consistently lights up on words that express degree or amount—comparatives, diminutives, and similar modifiers (e.g. “little,” “longer,” “better”).

the phrase "a little" followed by an adjective or adverb.

expressions that hedge or downplay magnitude by indicating a small or slight degree.

No Comments

No Known Activations

little/bit more

The neuron consistently lights up on words that express degree or amount—comparatives, diminutives, and similar modifiers (e.g. “little,” “longer,” “better”).

the phrase "a little" followed by an adjective or adverb.

expressions that hedge or downplay magnitude by indicating a small or slight degree.

No Comments

No Known Activations