INDEX

Explanations

the text is describing patterns

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

The neuron strongly activates on content‐bearing nouns and other key substantive words rather than on function words.

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

large numbers (typically in the thousands or ten-thousands range) representing quantities, measurements, or statistics.

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

common nouns in expository text (both concrete and abstract).

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

0.87

0.83

ز

0.82

0.81

0.80

0.79

**

0.73

ي

0.73

ال

0.72

POSITIVE LOGITS

 vibhav

1.05

лым

1.01

wellery

1.01

लाइड

0.97

 andolan

0.96

ны

0.94

 plabic

0.93

ъем

0.93

 fortalecer

0.93

 chhoti

0.93

Activations Density 0.000%

the text is describing patterns

The neuron strongly activates on content‐bearing nouns and other key substantive words rather than on function words.

large numbers (typically in the thousands or ten-thousands range) representing quantities, measurements, or statistics.

common nouns in expository text (both concrete and abstract).

No Comments

No Known Activations

the text is describing patterns

The neuron strongly activates on content‐bearing nouns and other key substantive words rather than on function words.

large numbers (typically in the thousands or ten-thousands range) representing quantities, measurements, or statistics.

common nouns in expository text (both concrete and abstract).

No Comments

No Known Activations