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

modulo operator (%) or parentheses (() (negative activations)

python-code · gemini-2.5-flash-lite

list index/slice

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

for

-0.02

(len

-0.02

any

-0.02

for

-0.02

len

-0.02

""

-0.02

join

-0.02

'.

-0.02

sum

-0.01

zip

-0.01

Positive Logits

0.02

0.01

[-

0.01

):↵

0.01

]):↵

0.01

-=

0.01

at

0.01

 initial

0.01

<=

0.01

Activations Density 72.280%