Circuit Sparsity

No connected neurons data available

Explanations

import collections

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

ble

-0.11

ors

-0.07

or

-0.06

tive

-0.06

text

-0.06

tes

-0.05

ts

-0.05

te

-0.04

rib

-0.04

Positive Logits

op

0.10

ram

0.08

oc

0.07

on

0.07

un

0.06

over

0.06

he

0.05

ree

0.04

al

0.03

si

0.03

Activations Density 49.941%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

sorted items by key reverse=True

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

 Calculate

-0.05

ters

-0.05

ter

-0.05

ault

-0.04

etween

-0.04

abs

-0.03

ta

-0.03

 default

-0.03

 math

-0.03

gle

-0.02

Positive Logits

 enumerate

0.05

['

0.04

[(

0.04

["

0.04

[-

0.04

[[

0.04

 []↵↵

0.03

 [↵

0.03

zip

0.03

Activations Density 71.219%