INDEX

Explanations

circa dates and circadian biology

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

The neuron detects the term "circa" followed by years or time periods, often identifying historical dates or time references.

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

The neuron is triggered by tokens beginning with “circ-” (e.g. “circa,” “circadian”).

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



-3.17

镕

-3.17

⽌

-2.91

芗

-2.78

蘼

-2.77

昻

-2.69

 使っ

-2.67

 空港

-2.67

 obrazy

-2.63

氿

-2.61

POSITIVE LOGITS

3.23

3.06

The

3.05

 Ganzen

2.84

<em>

2.70

’

2.70

er

2.70

 selben

2.67

2.66

Activations Density 0.003%

circa dates and circadian biology

The neuron detects the term "circa" followed by years or time periods, often identifying historical dates or time references.

The neuron is triggered by tokens beginning with “circ-” (e.g. “circa,” “circadian”).

No Comments

No Known Activations

circa dates and circadian biology

The neuron detects the term "circa" followed by years or time periods, often identifying historical dates or time references.

The neuron is triggered by tokens beginning with “circ-” (e.g. “circa,” “circadian”).

No Comments

No Known Activations