INDEX

Explanations

xmlns declarations

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

The neuron is triggered by occurrences of the character “Ø” (the Scandinavian letter) in tokens.

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

non-ASCII characters and XML namespace declarations/attributes.

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

the character "Ø" (specifically the Norwegian/Danish letter with a slash through it).

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

-2.95

By

-2.89

瑧

-2.83

.,

-2.77

 That

-2.75

 they

-2.67

一部

-2.63

”

-2.53

-2.52

);

-2.48

POSITIVE LOGITS

쨩

3.28

鸶

3.03

᯾

2.83

 नए

2.83

୩

2.78

Ꮓ

2.77

짭

2.73

凩

2.66

蹰

2.66

鲽

2.55

Activations Density 0.003%

xmlns declarations

The neuron is triggered by occurrences of the character “Ø” (the Scandinavian letter) in tokens.

non-ASCII characters and XML namespace declarations/attributes.

the character "Ø" (specifically the Norwegian/Danish letter with a slash through it).

No Comments

No Known Activations

xmlns declarations

The neuron is triggered by occurrences of the character “Ø” (the Scandinavian letter) in tokens.

non-ASCII characters and XML namespace declarations/attributes.

the character "Ø" (specifically the Norwegian/Danish letter with a slash through it).

No Comments

No Known Activations