INDEX

Explanations

From Victoria H Q Back

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

The neuron activates on numeric literals or sequences of digits in the text.

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

closing braces or brackets in code, particularly at the end of object or function definitions.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

end-of-block or closing syntax markers in code that indicate the termination of objects, function calls, or tags.

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

𝅥

-1.00

袛

-0.99

 crudo

-0.97

becomes

-0.88

assumed

-0.86

 inscrição

-0.86

𐐀

-0.86

 来自

-0.85

 搭配

-0.85

 sumptuous

-0.84

POSITIVE LOGITS

 after

1.25

 because

1.18

 before

1.16

by

1.10

 река

0.98

門口

0.96

敘

0.94

 bancos

0.94

 cargar

0.94

 segmentos

0.93

Activations Density 0.000%

From Victoria H Q Back

The neuron activates on numeric literals or sequences of digits in the text.

closing braces or brackets in code, particularly at the end of object or function definitions.

end-of-block or closing syntax markers in code that indicate the termination of objects, function calls, or tags.

No Comments

No Known Activations

From Victoria H Q Back

The neuron activates on numeric literals or sequences of digits in the text.

closing braces or brackets in code, particularly at the end of object or function definitions.

end-of-block or closing syntax markers in code that indicate the termination of objects, function calls, or tags.

No Comments

No Known Activations