Circuit Sparsity

No connected neurons data available

Explanations

the `name == 'main'` check (negative activations)

python-code · gemini-2.5-flash-lite

multiplication by 6 or 25

python-code · gemini-2.5-flash-lite

Auto-Interp Tools

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

Embeds

IFrame

Link

Negative Logits

 Calculate

-0.05

alculate

-0.04

alc

-0.04

prese

-0.04

 calculate

-0.04

valu

-0.03

_scores

-0.02

 float

-0.02

 comp

-0.02

 sorted

-0.01

Positive Logits

0.03

.ch

0.02

**

0.02

//

0.02

 index

0.02

_index

0.02

==

0.01

 root

0.01

**

0.01

Activations Density 48.174%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

float literal separator (negative activations)

python-code · gemini-2.5-flash-lite

len followed by parenthesis

python-code · gemini-2.5-flash-lite

Auto-Interp Tools

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

Embeds

IFrame

Link

Negative Logits

-0.02

(len

-0.02

len

-0.01

len

-0.01

for

-0.01

-0.00

0.00

Positive Logits

.add

0.01

([

0.01

ise

0.01

ar

0.01

abs

0.01

in

0.00

Activations Density 34.748%

the `__name__ == '__main__'` check (negative activations)

multiplication by 6 or 25

No Known Activations

float literal separator (negative activations)

len followed by parenthesis

No Known Activations

the `name == 'main'` check (negative activations)