INDEX

Explanations

primitive followed by man, crow, intestinal, neuro

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

the word "primitive" in scientific or historical contexts.

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

Triggered by @neilrathi

The main thing this neuron does is detect occurrences of the adjective “primitive” (and closely related historic/archaic descriptors).

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

赑

-2.41

身边的

-2.30

隳

-2.11

薷

-1.98

<bos>

-1.87

犼

-1.87

?"

-1.86

回来的

-1.79

xvii

-1.77

很赞

-1.76

POSITIVE LOGITS

”

2.11

However

1.94

 always

1.94

 While

1.91

ER

1.88

It

1.86

 still

1.85

🆚

1.79

as

1.79

1.77

Activations Density 0.012%

primitive followed by man, crow, intestinal, neuro

the word "primitive" in scientific or historical contexts.

The main thing this neuron does is detect occurrences of the adjective “primitive” (and closely related historic/archaic descriptors).

No Known Activations

primitive followed by man, crow, intestinal, neuro

the word "primitive" in scientific or historical contexts.

The main thing this neuron does is detect occurrences of the adjective “primitive” (and closely related historic/archaic descriptors).

No Known Activations