INDEX

Explanations

stimulating growth and receptors

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

words related to stimulation, particularly forms of the word "stimulating" and related concepts.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron fires strongly on various forms of the word “stimulate” (e.g. “stimulating,” “stimulation,” “stimulate”).

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

𖣘

-2.13

 øns

-1.98

 defying

-1.95

횃

-1.93

 lelaki

-1.88

 ifølge

-1.85

 fungerer

-1.84

 begyn

-1.83

 présidenti

-1.80

呜呜

-1.80

POSITIVE LOGITS

2.03

 هذه

1.85

1.77

ことができる

1.73

↵↵

1.72

$\

1.69

 peuvent

1.67

PasswordEncoder

1.66

but

1.66

Activations Density 0.033%

stimulating growth and receptors

words related to stimulation, particularly forms of the word "stimulating" and related concepts.

The neuron fires strongly on various forms of the word “stimulate” (e.g. “stimulating,” “stimulation,” “stimulate”).

No Comments

No Known Activations

stimulating growth and receptors

words related to stimulation, particularly forms of the word "stimulating" and related concepts.

The neuron fires strongly on various forms of the word “stimulate” (e.g. “stimulating,” “stimulation,” “stimulate”).

No Comments

No Known Activations