Circuit Sparsity

No connected neurons data available

Explanations

function call parenthesis (negative activations)

python-code · gemini-2.5-flash-lite

except or with followed by open

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

ron

-0.06

 heap

-0.05

 heapq

-0.05

.pop

-0.04

 Tuple

-0.03

queue

-0.03

left

-0.03

orted

-0.03

erge

-0.03

 sorted

-0.03

Positive Logits

[(

0.04

 representing

0.03

","

0.03

 between

0.02

 heuristic

0.02

['

0.02

["

0.02

.set

0.02

 weights

0.02

][

0.02

Activations Density 87.741%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

sqlite3 module and methods (negative activations)

python-code · gemini-2.5-flash-lite

for loop structure

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

isited

-0.04

-0.03

 create

-0.03

.random

-0.03

orted

-0.02

maining

-0.02

visited

-0.02

quired

-0.02

alculate

-0.02

use

-0.02

Positive Logits

0.03

}")<|

0.02

unc

0.01

 temp

0.01

in

0.01

ery

0.01

Ń

0.01

ase

0.01

Activations Density 40.469%