INDEX

Circuit Sparsity

No connected neurons data available

Explanations

.p import or .p execute or .p message

assignment of variables (negative activations)

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

Embeds

IFrame

Link

Negative Logits

.position

-0.06

 coordinates

-0.04

alse

-0.04

uel

-0.04

rue

-0.04

 True

-0.03

_coords

-0.03

False

-0.03

_position

-0.03

_cost

-0.03

POSITIVE LOGITS

0.03

(min

0.03

(max

0.03

(maze

0.03

(range

0.03

(map

0.03

(route

0.03

(de

0.03

(op

0.03

(N

0.03

Activations Density 100.000%