INDEX

Explanations

behaves differently

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

The neuron fires on verbs that describe how something “does” or “performs” (e.g. fare, fairing, perform/performed, behave/behaving, etc.).

oai_token-act-pair · o4-mini 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

of

-3.88

but

-2.45

(/^

-1.96

棪

-1.95

nological

-1.84

for

-1.82

naments

-1.82

omorphisms

-1.80

ichord

-1.73

 istimewa

-1.70

POSITIVE LOGITS

1.70

</h2>

1.70

 útiles

1.54

 вещи

1.45

十分的

1.41

 όπως

1.38

 necesarios

1.38

 entirety

1.36

↵

1.34

</h4>

1.32

Activations Density 0.139%

behaves differently

The neuron fires on verbs that describe how something “does” or “performs” (e.g. fare, fairing, perform/performed, behave/behaving, etc.).

No Comments

No Known Activations

behaves differently

The neuron fires on verbs that describe how something “does” or “performs” (e.g. fare, fairing, perform/performed, behave/behaving, etc.).

No Comments

No Known Activations

behaves differently

The neuron fires on verbs that describe how something “does” or “performs” (e.g. fare, fairing, perform/​performed, behave/​behaving, etc.).

No Comments

No Known Activations

behaves differently

The neuron fires on verbs that describe how something “does” or “performs” (e.g. fare, fairing, perform/​performed, behave/​behaving, etc.).

No Comments

No Known Activations

The neuron fires on verbs that describe how something “does” or “performs” (e.g. fare, fairing, perform/performed, behave/behaving, etc.).

The neuron fires on verbs that describe how something “does” or “performs” (e.g. fare, fairing, perform/performed, behave/behaving, etc.).