INDEX

Explanations

electrocardiogram (ECG)

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

medical and technical acronyms, particularly "ECG" (electrocardiogram) and similar terms.

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

The neuron responds to capitalized terms—especially names and multi‐letter acronyms (e.g. “Pallone,” “ECG”).

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

 ausein

-2.69

寕

-2.63

Ꭳ

-2.53

鉺

-2.48

亖

-2.47

seded

-2.47

俛

-2.47

阄

-2.42

 emporio

-2.41

簟

-2.36

POSITIVE LOGITS

as

3.25

3.16

↵↵

2.84

on

2.83

2.73

are

2.70

ra

2.69

“

2.69

2.56

al

2.53

Activations Density 0.008%

electrocardiogram (ECG)

medical and technical acronyms, particularly "ECG" (electrocardiogram) and similar terms.

The neuron responds to capitalized terms—especially names and multi‐letter acronyms (e.g. “Pallone,” “ECG”).

No Comments

No Known Activations

electrocardiogram (ECG)

medical and technical acronyms, particularly "ECG" (electrocardiogram) and similar terms.

The neuron responds to capitalized terms—especially names and multi‐letter acronyms (e.g. “Pallone,” “ECG”).

No Comments

No Known Activations