INDEX

Explanations

special characters and mistakes

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

The neuron activates on sequences of asterisks (e.g. , , ) used for emphasis or marking text.

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

焕

-1.34

 najbol

-1.31

 način

-1.30

сної

-1.30

 pomen

-1.27

 obligado

-1.27



-1.25

高さ

-1.24

 igra

-1.23

 stalo

-1.23

POSITIVE LOGITS

1.51

 avan

1.25

 跳转至

1.24

</em>

1.23

‚

1.22

 दोनों

1.20

 produisons

1.18

uno

1.14

 kleine

1.13

感が

1.13

Activations Density 0.005%

special characters and mistakes

The neuron activates on sequences of asterisks (e.g. , , ) used for emphasis or marking text.

No Comments

No Known Activations

special characters and mistakes

The neuron activates on sequences of asterisks (e.g. , , ) used for emphasis or marking text.

No Comments

No Known Activations

special characters and mistakes

The neuron activates on sequences of asterisks (e.g. *, **, ***) used for emphasis or marking text.

No Comments

No Known Activations

special characters and mistakes

The neuron activates on sequences of asterisks (e.g. *, **, ***) used for emphasis or marking text.

No Comments

No Known Activations

The neuron activates on sequences of asterisks (e.g. , , ) used for emphasis or marking text.

The neuron activates on sequences of asterisks (e.g. , , ) used for emphasis or marking text.