INDEX

Explanations

in dollars, a, Blender, bytes

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

The neuron strongly activates on occurrences of the preposition “in.”

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

the preposition "in" when it appears in formal, procedural, or technical contexts.

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

the preposition that denotes inclusion, location, or time (being inside, within, or during).

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

ในปี

0.88

decade

0.83

在北京

0.83

Mfg

0.82

 उसमें

0.80

س

0.80

Người

0.79

ων

0.77

Hugh

0.76

POSITIVE LOGITS

 accordance

1.74

 وفي

1.23

 vitro

1.22

 vacuo

1.12

 conjunction

1.10

 maniera

1.10

 pursuance

1.10

 рамках

1.08

 order

1.07

 situ

1.06

Activations Density 0.001%

in dollars, a, Blender, bytes

The neuron strongly activates on occurrences of the preposition “in.”

the preposition "in" when it appears in formal, procedural, or technical contexts.

the preposition that denotes inclusion, location, or time (being inside, within, or during).

No Comments

No Known Activations