INDEX

Explanations

Darren or tyrosine

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

This neuron detects mentions of the amino acid tyrosine and first names (particularly "Darren").

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

This neuron fires on capitalized proper nouns—particularly author names (e.g. “Darren”) and molecule names like “Tyrosine.”

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

 There

-3.05

on

-2.66

The

-2.64

To

-2.56

我们

-2.34

 With

-2.33

ra

-2.31

Of

-2.28

POSITIVE LOGITS

蟶

3.64

 撮っ

3.31

だけです

3.30

3.22

鷓

2.75

ༀ

2.70

槩

2.64

尛

2.52

蟜

2.52

 間取り

2.52

Activations Density 0.013%

Darren or tyrosine

This neuron detects mentions of the amino acid tyrosine and first names (particularly "Darren").

This neuron fires on capitalized proper nouns—particularly author names (e.g. “Darren”) and molecule names like “Tyrosine.”

No Comments

No Known Activations

Darren or tyrosine

This neuron detects mentions of the amino acid tyrosine and first names (particularly "Darren").

This neuron fires on capitalized proper nouns—particularly author names (e.g. “Darren”) and molecule names like “Tyrosine.”

No Comments

No Known Activations