INDEX

Explanations

morning and breakfast

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

The neuron strongly activates on mentions of the morning—especially words like “morning,” “Mornings,” and “breakfast” (including associated time indications).

oai_token-act-pair · o4-mini Triggered by @jyhe0408

references to the morning time of day—breakfast-related content, coffee/energy cues, and early-hour schedules.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

the word "morning" or its variations in different languages.

oai_token-act-pair · claude-4-5-sonnet 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

</strong>

-1.88

$,

-1.63

');

-1.59

‐

-1.53

$.

-1.52

gegen

-1.52

葑

-1.52

lgari

-1.50

{"

-1.48

POSITIVE LOGITS

 morning

1.99

 breakfast

1.64

 venuto

1.61



1.59

起床

1.58

morning

1.53

breakfast

1.51



1.45

 colazione

1.43

 tomba

1.41

Activations Density 0.037%

morning and breakfast

The neuron strongly activates on mentions of the morning—especially words like “morning,” “Mornings,” and “breakfast” (including associated time indications).

references to the morning time of day—breakfast-related content, coffee/energy cues, and early-hour schedules.

the word "morning" or its variations in different languages.

No Comments

No Known Activations

morning and breakfast

The neuron strongly activates on mentions of the morning—especially words like “morning,” “Mornings,” and “breakfast” (including associated time indications).

references to the morning time of day—breakfast-related content, coffee/energy cues, and early-hour schedules.

the word "morning" or its variations in different languages.

No Comments

No Known Activations