INDEX

Explanations

AI image generators, libraries, thresholds

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

The neuron strongly activates on uncommon or out‐of‐vocabulary tokens—rare words, acronyms, and unusual strings.

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

colons that introduce direct speech, quotes, or listed information in formal or structured text.

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

parenthetical or appositive insertions and other separator-style constructions (like parentheses, slashes, dashes, and colons) that introduce asides or clarifications.

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

 teorías

0.88

 baseApiPath

0.87

 reflectivity

0.84

 investigaciones

0.80

 strony

0.80

 signification

0.77

 ہمارے

0.77

应用的

0.77

 inventories

0.77

 decimos

0.76

POSITIVE LOGITS

^(

0.71

0.70

 Adapted

0.69

adapted

0.68

0.65

 Lyrics

0.63

 erhielt

0.63

 Asoci

0.61

ре

0.60

igung

0.60

Activations Density 0.000%

AI image generators, libraries, thresholds

The neuron strongly activates on uncommon or out‐of‐vocabulary tokens—rare words, acronyms, and unusual strings.

colons that introduce direct speech, quotes, or listed information in formal or structured text.

parenthetical or appositive insertions and other separator-style constructions (like parentheses, slashes, dashes, and colons) that introduce asides or clarifications.

No Comments

No Known Activations