INDEX

Explanations

personal pronouns

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

The neuron strongly activates on personal pronouns addressing or referring to people (especially first- and second-person pronouns like “you,” “me,” “them”).

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

the word "you" in direct address to the reader.

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

second-person direct address (pronouns/possessives referring to the reader), with occasional sensitivity to first-person self-reference.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_31_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

 auprès

0.59

 معاكم

0.59

ότερα

0.57

ให้กับ

0.57

 بالنسبة

0.56

qc

0.55

ਵਾ

0.54

த்துடன்

0.53

 لدينا

0.53

 đối

0.53

POSITIVE LOGITS

 berupa

0.59

 personally

0.59

 berbentuk

0.55

 ను

0.53

 напрямую

0.52

 personalmente

0.51

 verand

0.51

 guys

0.50

ſelf

0.50

 pessoais

0.49

Activations Density 0.213%

personal pronouns

The neuron strongly activates on personal pronouns addressing or referring to people (especially first- and second-person pronouns like “you,” “me,” “them”).

the word "you" in direct address to the reader.

second-person direct address (pronouns/possessives referring to the reader), with occasional sensitivity to first-person self-reference.

No Comments

No Known Activations

personal pronouns

The neuron strongly activates on personal pronouns addressing or referring to people (especially first- and second-person pronouns like “you,” “me,” “them”).

the word "you" in direct address to the reader.

second-person direct address (pronouns/possessives referring to the reader), with occasional sensitivity to first-person self-reference.

No Comments

No Known Activations