INDEX

Explanations

code comments and keywords

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

inline comments in code, particularly those explaining or describing what follows.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron flags tokens that occur inside code comments.

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

 then

-1.41

这样的

-1.31

 avulla

-1.23

を行いました

-1.22

çadas

-1.22

 такое

-1.20

Langkah

-1.20

}{

-1.20

aupun

-1.20

 atmosfera

-1.19

POSITIVE LOGITS

and

1.76

AÇÃO

1.58

the

1.52

͊

1.35

``

1.34

1.33

 kimdir

1.30

 např

1.30

1.25

 arid

1.24

Activations Density 0.009%

code comments and keywords

inline comments in code, particularly those explaining or describing what follows.

The neuron flags tokens that occur inside code comments.

No Comments

No Known Activations

code comments and keywords

inline comments in code, particularly those explaining or describing what follows.

The neuron flags tokens that occur inside code comments.

No Comments

No Known Activations