INDEX

Explanations

code comments and mathematical notation

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

The neuron fires on tokens that mark “comment” or “code/math” block delimiters (e.g. /**, /, /, ```, $, $$, etc.).

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

↵

-1.55

For

-1.47

And

-1.38

 dodatkowe

-1.38

-1.33

-1.32

艘

-1.23

 generalmente

-1.23

-1.22

POSITIVE LOGITS

</strong>

2.33

</i>

1.70

 verhind

1.59

龶

1.55

 Meksi

1.51

"")

1.48

</u>

1.47

""}

1.45

</em>

1.44

💓

1.44

Activations Density 0.112%

code comments and mathematical notation

The neuron fires on tokens that mark “comment” or “code/math” block delimiters (e.g. /**, /, /, ```, $, $$, etc.).

No Comments

No Known Activations

code comments and mathematical notation

The neuron fires on tokens that mark “comment” or “code/math” block delimiters (e.g. /**, /, /, ```, $, $$, etc.).

No Comments

No Known Activations

code comments and mathematical notation

The neuron fires on tokens that mark “comment” or “code/math” block delimiters (e.g. /**, */, /*, ```, $, $$, etc.).

No Comments

No Known Activations

code comments and mathematical notation

The neuron fires on tokens that mark “comment” or “code/math” block delimiters (e.g. /**, */, /*, ```, $, $$, etc.).

No Comments

No Known Activations

The neuron fires on tokens that mark “comment” or “code/math” block delimiters (e.g. /**, /, /, ```, $, $$, etc.).

The neuron fires on tokens that mark “comment” or “code/math” block delimiters (e.g. /**, /, /, ```, $, $$, etc.).