INDEX

Explanations

diagnosing medical conditions

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

numbers in text, particularly when referring to quantities, dates, or measurements.

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

The neuron detects numeric expressions (numbers, ages, dates, counts, costs, etc.) 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_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

 mereka

-1.91

 relâche

-1.70

ίναι

-1.62

Kamera

-1.49

Алек

-1.47

 nedeniyle

-1.47

 zobra

-1.46

 uñas

-1.44

 réfugi

-1.43

Waga

-1.42

POSITIVE LOGITS

2.16

 polícia

1.70

 into

1.52

 this

1.44

 there

1.39

 femininos

1.39

“

1.36

an

1.35

‘

1.34

谂

1.33

Activations Density 0.001%

diagnosing medical conditions

numbers in text, particularly when referring to quantities, dates, or measurements.

The neuron detects numeric expressions (numbers, ages, dates, counts, costs, etc.) wherever they appear in the text.

No Comments

No Known Activations

diagnosing medical conditions

numbers in text, particularly when referring to quantities, dates, or measurements.

The neuron detects numeric expressions (numbers, ages, dates, counts, costs, etc.) wherever they appear in the text.

No Comments

No Known Activations