INDEX

Explanations

Elisa and ELISA assays

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

proper names of people, particularly in scientific or journalistic contexts.

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

The neuron strongly activates on capitalized tokens—particularly proper names and acronyms (e.g. personal names like “Kirsch,” “Connolly,” “Elisa” and all-caps abbreviations like “ELISA”).

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

at

-2.55

-2.41

 verschiedenen

-2.31

-2.27

霎

-2.17

 zahlreichen

-2.14

‘

-2.13

 abnormally

-2.13

↵

-2.13

<bos>

-2.13

POSITIVE LOGITS

捽

2.89

2.58

2.47

 parteci

2.47

踯

2.45

仉

2.44

 начинают

2.39

 verhind

2.38

2.31

 potranno

2.28

Activations Density 0.074%

Elisa and ELISA assays

proper names of people, particularly in scientific or journalistic contexts.

The neuron strongly activates on capitalized tokens—particularly proper names and acronyms (e.g. personal names like “Kirsch,” “Connolly,” “Elisa” and all-caps abbreviations like “ELISA”).

No Comments

No Known Activations

Elisa and ELISA assays

proper names of people, particularly in scientific or journalistic contexts.

The neuron strongly activates on capitalized tokens—particularly proper names and acronyms (e.g. personal names like “Kirsch,” “Connolly,” “Elisa” and all-caps abbreviations like “ELISA”).

No Comments

No Known Activations