INDEX

Explanations

loop variable or index in code

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

the variable "i" in programming code, particularly in C-style loop declarations and statements.

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

The neuron is detecting numeric literal tokens (i.e. numbers) in the code.

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

ens

-1.45

 verschiedene

-1.39

 कुछ

-1.38

 Thankfully

-1.36

 Rather

-1.34

arians

-1.34

 Certain

-1.30

த்து

-1.29

 Temmuz

-1.28

белый

-1.28

POSITIVE LOGITS

who

1.63

can

1.49

仍在

1.44

ارتمان

1.37

 فلزی

1.30

its

1.27

 yielded

1.27

 should

1.23

 allowed

1.21



1.21

Activations Density 0.007%

loop variable or index in code

the variable "i" in programming code, particularly in C-style loop declarations and statements.

The neuron is detecting numeric literal tokens (i.e. numbers) in the code.

No Comments

No Known Activations

loop variable or index in code

the variable "i" in programming code, particularly in C-style loop declarations and statements.

The neuron is detecting numeric literal tokens (i.e. numbers) in the code.

No Comments

No Known Activations