INDEX

Explanations

family members

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

The neuron activates on words referring to one’s children—specifically “son” or “daughter.”

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

mentions of a speaker’s children, especially first-person possessive references to sons or daughters.

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

references to the speaker's son or daughter in personal narratives.

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-1.55

䊐

-1.46

for

-1.32

bzw

-1.24

 یا

-1.23

 undermines

-1.22

-1.18

-1.15

หรือ

-1.15

POSITIVE LOGITS

 also

1.86

 также

1.30

 finally

1.25

 even

1.24

 semelhantes

1.20

 similarly

1.20

 vollständige

1.20

 Phòng

1.17

 sogen

1.16

 également

1.16

Activations Density 0.035%

family members

The neuron activates on words referring to one’s children—specifically “son” or “daughter.”

mentions of a speaker’s children, especially first-person possessive references to sons or daughters.

references to the speaker's son or daughter in personal narratives.

No Comments

No Known Activations

family members

The neuron activates on words referring to one’s children—specifically “son” or “daughter.”

mentions of a speaker’s children, especially first-person possessive references to sons or daughters.

references to the speaker's son or daughter in personal narratives.

No Comments

No Known Activations