INDEX

Explanations

len, sorted, query, parseFloat

The neuron activates on numeric literals—especially floating‐point numbers appearing in code or text.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 Math

0.61

Math

0.57

 "");

0.56

GLOBALS

0.49

(""))

0.48

"")

0.48

(_.

0.48

('').

0.47

("

0.46

 "").

0.46

POSITIVE LOGITS

Figura

0.45

⎦

0.45

 exploit

0.43

 যৌগ

0.43

 dient

0.42

{}

0.42

cui

0.41

[-]

0.41

 indexing

0.40

 topologies

0.40

Activations Density 0.000%