Circuit Sparsity

No connected neurons data available

Explanations

itertools.product and entropy

python-code · gemini-2.5-flash-lite

method call with parentheses () (negative activations)

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

print

-0.05

ound

-0.05

lo

-0.04

lo

-0.04

Re

-0.03

or

-0.03

der

-0.03

ad

-0.03

-0.02

Positive Logits

xF

0.07

ize

0.06

nt

0.05

0.04

loat

0.04

 [↵

0.03

the

0.03

self

0.03

ket

0.03

ger

0.03

Activations Density 100.000%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

sum variable initialization and accumulation

python-code · gemini-2.5-flash-lite

function call parenthesis (negative activations)

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

udent

-0.09

[str

-0.08

hicle

-0.07

 student

-0.06

 best

-0.06

mmand

-0.06

his

-0.06

_move

-0.06

 move

-0.06

['

-0.05

Positive Logits

rue

0.05

div

0.05

á

0.04

(current

0.04

graph

0.04

Æ

0.04

[current

0.03

gram

0.03

blem

0.03

 current

0.03

Activations Density 100.000%