Circuit Sparsity

No connected neurons data available

Explanations

list items or sys.exit

python-code · gemini-2.5-flash-lite

last element of list (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

city

-0.09

_city

-0.08

 city

-0.08

_cities

-0.07

 cities

-0.07

gion

-0.07

ity

-0.07

ities

-0.07

ange

-0.06

udent

-0.06

Positive Logits

dp

0.13

_comb

0.09

_counts

0.07

osition

0.06

_sum

0.06

 comb

0.06

os

0.06

inations

0.06

ati

0.06

pos

0.05

Activations Density 100.000%

No Known Activations

Prev Next

Circuit Sparsity

No connected neurons data available

Explanations

variable assignment or loop

python-code · gemini-2.5-flash-lite

`def` keyword or `optimizer` (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

-0.03

 depth

-0.03

mmand

-0.03

sim

-0.03

-0.02

_line

-0.02

sc

-0.02

 visited

-0.02

Positive Logits

apac

0.07

ong

0.06

_cost

0.05

 cost

0.05

apacity

0.04

out

0.04

ove

0.03

0.02

rice

0.02

ross

0.02

Activations Density 100.000%