INDEX

Explanations

public class, essential oils

np_acts-logits-general · gemini-2.5-flash-lite

programming and technical syntax patterns, particularly in code and mathematical expressions.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron fires on standalone numerals (digits and multi‐digit number tokens) wherever they appear in the text.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zené

-0.89

 míst

-0.88

 cóc

-0.88

尽量

-0.87

tê

-0.85

ısını

-0.85

lierte

-0.84

 höl

-0.83

werf

-0.81

Σ

-0.80

POSITIVE LOGITS

 with

1.25

ביוגרפיה

1.01

 like

1.01

 different

0.98

 bốn

0.95

 while

0.93

two

0.91

 seven

0.89

 Riti

0.87

ᴢ

0.86

Activations Density 0.004%

public class, essential oils

programming and technical syntax patterns, particularly in code and mathematical expressions.

The neuron fires on standalone numerals (digits and multi‐digit number tokens) wherever they appear in the text.

No Comments

No Known Activations

public class, essential oils

programming and technical syntax patterns, particularly in code and mathematical expressions.

The neuron fires on standalone numerals (digits and multi‐digit number tokens) wherever they appear in the text.

No Comments

No Known Activations