INDEX

Explanations

mathematical notation and chemical symbols

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

chemical formulas and mathematical notation in brackets or parentheses.

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

The neuron detects numeric annotations in brackets or parentheses—especially isotope or chemical‐label numbers (e.g. “[(40.75 ^3H)]” or similar)—embedded in the text.

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/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



-1.84

-1.82

-1.75

その

-1.71

真的很

-1.70

 entram

-1.70

从来

-1.60

為什麼

-1.59

</strong>

-1.59

本来

-1.58

POSITIVE LOGITS

1.64

èmes

1.60

 which

1.59

two

1.59

чению

1.51

 while

1.50

");

1.50

 burgeoning

1.46

 terv

1.45

 اصفه

1.42

Activations Density 0.001%

mathematical notation and chemical symbols

chemical formulas and mathematical notation in brackets or parentheses.

The neuron detects numeric annotations in brackets or parentheses—especially isotope or chemical‐label numbers (e.g. “[(40.75 ^3H)]” or similar)—embedded in the text.

No Comments

No Known Activations

mathematical notation and chemical symbols

chemical formulas and mathematical notation in brackets or parentheses.

The neuron detects numeric annotations in brackets or parentheses—especially isotope or chemical‐label numbers (e.g. “[(40.75 ^3H)]” or similar)—embedded in the text.

No Comments

No Known Activations