Circuit Sparsity

No connected neurons data available

Explanations

def keyword or tkinter Button

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

-0.11

-0.07

tices

-0.07

ffe

-0.07

tity

-0.06

ti

-0.06

imum

-0.05

grid

-0.05

tic

-0.04

tive

-0.04

Positive Logits

0.09

0.07

 This

0.06

gs

0.05

value

0.04

.d

0.04

que

0.04

Activations Density 4.145%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

.append method calls (negative activations)

python-code · gemini-2.5-flash-lite

variable assignment or comparison

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

out

-0.04

 found

-0.03

ist

-0.03

qrt

-0.03

in

-0.02

rent

-0.02

inary

-0.02

out

-0.02

ax

-0.02

ous

-0.02

Positive Logits

0.02

ves

0.01

end

0.01

ed

0.01

ati

0.01

ub

0.00

Activations Density 43.171%