Circuit Sparsity

No connected neurons data available

Explanations

identifier followed by assignment (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

instance

-0.06

join

-0.06

riority

-0.05

cores

-0.05

 sorted

-0.05

[str

-0.05

keys

-0.04

[int

-0.04

output

-0.04

hip

-0.04

Positive Logits

ili

0.18

gle

0.17

ility

0.16

zz

0.15

ount

0.14

vious

0.14

ket

0.14

ilities

0.14

ble

0.13

gor

0.13

Activations Density 6.442%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

substring or slice end

python-code · gemini-2.5-flash-lite

function definition parenthesis (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

rite

-0.08

Į

-0.07

þ

-0.07

ü

-0.07

ö

-0.07

À

-0.07

<invalid_2046>

-0.07

÷

-0.07

ù

-0.07

ý

-0.07

Positive Logits

 representing

0.07

0.05

 that

0.05

 each

0.04

the

0.04

]][

0.04

 represe

0.04

 break

0.04

ast

0.04

 minimum

0.03

Activations Density 100.000%