INDEX

Explanations

items for sale

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

This neuron activates on first-person, self-referential pitches or classifieds—i.e. sentences where someone says “I” and offers to sell or advertise something.

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

sentence-ending periods in product listings, classified ads, and other commercial or transactional text.

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

īt

-1.16

 when

-1.12

 each

-1.11

成为

-0.93

૨

-0.91

 different

-0.91

紀

-0.86

эг

-0.85

 where

-0.84

Allocate

-0.84

POSITIVE LOGITS

 нынеш

1.16

 available

1.09

 кому

1.02

 núm

1.00

ヨー

1.00

 mevcut

1.00

 offer

0.99

ないです

0.99

 priced

0.98

 смогут

0.97

Activations Density 0.020%

items for sale

This neuron activates on first-person, self-referential pitches or classifieds—i.e. sentences where someone says “I” and offers to sell or advertise something.

sentence-ending periods in product listings, classified ads, and other commercial or transactional text.

No Comments

No Known Activations

items for sale

This neuron activates on first-person, self-referential pitches or classifieds—i.e. sentences where someone says “I” and offers to sell or advertise something.

sentence-ending periods in product listings, classified ads, and other commercial or transactional text.

No Comments

No Known Activations