Circuit Sparsity

No connected neurons data available

Explanations

range function arguments (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

 best

-0.12

.random

-0.12

 random

-0.10

_cities

-0.10

random

-0.09

 cities

-0.08

Ĥ

-0.08

ateg

-0.07

 sele

-0.07

_city

-0.07

Positive Logits

0.13

[str

0.12

0.11

_string

0.10

_str

0.09

ood

0.08

str

0.07

(str

0.07

.split

0.07

Activations Density 100.000%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

operator keyword or method call

python-code · gemini-2.5-flash-lite

assignment to list elements (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

div

-0.04

ory

-0.04

hest

-0.04

 ]↵

-0.04

_name

-0.04

reshold

-0.04

 }↵

-0.04

_j

-0.03

ren

-0.03

resh

-0.03

Positive Logits

lat

0.07

itude

0.06

lat

0.06

ge

0.05

xF

0.05

 Returns

0.05

igh

0.05

_city

0.05

gion

0.04

city

0.04

Activations Density 100.000%