INDEX

Circuit Sparsity

No connected neurons data available

Explanations

attribute or attr access

numeric literal in a list (negative activations)

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

_matrix

-0.06

graph

-0.05

nx

-0.05

ny

-0.04

.con

-0.04

 matrix

-0.03

-0.02

dx

-0.02

.txt

-0.02

POSITIVE LOGITS

mmon

0.09

mmand

0.09

losest

0.09

straints

0.09

apac

0.09

utput

0.09

timal

0.09

dint

0.08

alculate

0.08

mport

0.08

Activations Density 100.000%