INDEX

Explanations

lutein, luteolin, luteum, luteal

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

the word stem "lute" followed by variations like "in", "al", "olin", or "um" in biological/medical contexts.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron activates on occurrences of “lute‐” (e.g. luteum, luteal, luteinizing) – i.e. words containing the “lute” prefix.

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

Negative Logits

鶲

-3.41



-2.97

⚢

-2.81

㐂

-2.77

鲮

-2.77

㍑

-2.72

Ꭳ

-2.67

栳

-2.56

for

-2.50



-2.48

POSITIVE LOGITS

↵

2.70

</strong>

2.34

2.17

 explores

2.14

作って

2.09

".

2.08

enablog

2.05

2.02

 diminished

1.99

 כמו

1.98

Activations Density 0.006%

lutein, luteolin, luteum, luteal

the word stem "lute" followed by variations like "in", "al", "olin", or "um" in biological/medical contexts.

The neuron activates on occurrences of “lute‐” (e.g. luteum, luteal, luteinizing) – i.e. words containing the “lute” prefix.

No Known Activations

lutein, luteolin, luteum, luteal

the word stem "lute" followed by variations like "in", "al", "olin", or "um" in biological/medical contexts.

The neuron activates on occurrences of “lute‐” (e.g. luteum, luteal, luteinizing) – i.e. words containing the “lute” prefix.

No Known Activations