INDEX

Explanations

in a phrase

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

The neuron detects words that signal being situated or placed inside a location or state (e.g. “in,” “isolated,” “secluded”).

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

locative prepositions introducing where something is or happens.

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

the preposition "in" when it indicates physical location or enclosure within a space.

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

 flera

-1.77

ものを

-1.69

 roligt

-1.62

you

-1.56

 olika

-1.55

 recogida

-1.50

zeniem

-1.50

 svårt

-1.50

 säs

-1.48

 strå

-1.47

POSITIVE LOGITS

 there

1.75

for

1.55

by

1.54

one

1.51

at

1.46

usahaan

1.45

 verhalen

1.45

Особенности

1.43

the

1.41

on

1.39

Activations Density 0.060%

in a phrase

The neuron detects words that signal being situated or placed inside a location or state (e.g. “in,” “isolated,” “secluded”).

locative prepositions introducing where something is or happens.

the preposition "in" when it indicates physical location or enclosure within a space.

No Comments

No Known Activations

in a phrase

The neuron detects words that signal being situated or placed inside a location or state (e.g. “in,” “isolated,” “secluded”).

locative prepositions introducing where something is or happens.

the preposition "in" when it indicates physical location or enclosure within a space.

No Comments

No Known Activations