Circuit Sparsity

No connected neurons data available

Explanations

parse or partition function calls

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

atus

-0.02

ost

-0.01

 return

-0.01

 conne

-0.01

_for

-0.01

<|

-0.01

hi

-0.01

spe

-0.01

Positive Logits

 parse

0.05

par

0.03

gre

0.03

light

0.03

0.02

(N

0.02

loat

0.02

.strip

0.02

qrt

0.02

.split

0.02

Activations Density 49.979%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

number literal

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

-0.04

None

-0.03

or

-0.03

 None

-0.03

and

-0.03

=None

-0.03

-0.02

.random

-0.02

Positive Logits

<=

0.06

If

0.04

lse

0.04

lif

0.03

if

0.03

 elif

0.03

rior

0.02

qrt

0.02

Activations Density 94.355%