INDEX

Explanations

states of growth

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

phrases describing growth, particularly when something is "growing" or "fast-growing".

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron detects descriptive terms—especially “growing” (and intensified forms like “fastest-growing”)—that signal rapid expansion or increase.

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

Negative Logits

 that

-1.65

to

-1.44

It

-1.41

いいのか

-1.41

 probable

-1.36

лета

-1.36

𖣘

-1.35

That

-1.34

Besides

-1.34

 likely

-1.34

POSITIVE LOGITS

↵↵

1.52

 ギャラリー

1.41

 наших

1.40

اته

1.37

."

1.29

 brancas

1.29

gericht

1.28

kurtka

1.27

 creciente

1.23

 coloridas

1.22

Activations Density 0.057%

states of growth

phrases describing growth, particularly when something is "growing" or "fast-growing".

The neuron detects descriptive terms—especially “growing” (and intensified forms like “fastest-growing”)—that signal rapid expansion or increase.

No Known Activations

states of growth

phrases describing growth, particularly when something is "growing" or "fast-growing".

The neuron detects descriptive terms—especially “growing” (and intensified forms like “fastest-growing”)—that signal rapid expansion or increase.

No Known Activations