INDEX

Explanations

acknowledging common traits or difficulties

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

The neuron strongly activates on uncommon, low-frequency content words.

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

garbled or corrupted text that appears to be machine-generated or scraped web content.

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

specialized, technical-sounding terminology and formal nouns, especially those related to measurements, processes, or professional domains.

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

sess

0.86

ดำ

0.86

рения

0.81

callbacks

0.76

 правительства

0.75

 biochem

0.75

dens

0.75

saya

0.74

sterdam

0.72

descricao

0.72

POSITIVE LOGITS

 afferma

0.75

unu

0.72

지만

0.68

 posti

0.68

곧

0.68

 costitu

0.67

 підприєм

0.67

 promu

0.67

 affirme

0.67

 realtà

0.67

Activations Density 0.000%

acknowledging common traits or difficulties

The neuron strongly activates on uncommon, low-frequency content words.

garbled or corrupted text that appears to be machine-generated or scraped web content.

specialized, technical-sounding terminology and formal nouns, especially those related to measurements, processes, or professional domains.

No Comments

No Known Activations