Circuit Sparsity

No connected neurons data available

Explanations

modulo operator with even/odd check (negative activations)

python-code · gemini-2.5-flash-lite

if name

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

place

-0.02

.t

-0.01

ost

-0.01

.get

-0.01

ol

-0.01

 True

-0.01

0.00

Positive Logits

loat

0.03

.in

0.03

sys

0.03

 float

0.02

.f

0.01

 math

0.01

.m

0.01

Activations Density 58.948%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

`for` loop with `range` (negative activations)

python-code · gemini-2.5-flash-lite

module and class instantiation

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

fset

-0.01

 possible

-0.01

hor

-0.01

 directions

-0.01

 neighbors

-0.01

 adjac

-0.01

 moves

-0.01

dx

-0.01

adj

-0.01

 direction

-0.01

Positive Logits

 form

0.01

If

0.00

 optim

0.00

 results

0.00

_m

0.00

Activations Density 99.404%

modulo operator with even/odd check (negative activations)

if __name__

No Known Activations

`for` loop with `range` (negative activations)

module and class instantiation

No Known Activations

if name