INDEX

Explanations

food items eaten

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

organisms consuming food or descriptions of eating patterns in animals and plants.

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

The neuron fires on mentions of organisms’ food items—that is, nouns naming what a species eats (e.g. algae, grasses, sap, etc.).

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

ísimas

-1.34

냈

-1.30

 prêts

-1.21

 baumwolle

-1.16

目で

-1.13

ᵑ

-1.13

 lakini

-1.09

 créées

-1.09

 arbol

-1.09

istr

-1.08

POSITIVE LOGITS

 often

1.39

 from

1.37

or

1.30

</i>

1.30

 provide

1.29

 ensure

1.27

add

1.23

 cuando

1.22

 иногда

1.19

 during

1.17

Activations Density 0.099%

food items eaten

organisms consuming food or descriptions of eating patterns in animals and plants.

The neuron fires on mentions of organisms’ food items—that is, nouns naming what a species eats (e.g. algae, grasses, sap, etc.).

No Comments

No Known Activations

food items eaten

organisms consuming food or descriptions of eating patterns in animals and plants.

The neuron fires on mentions of organisms’ food items—that is, nouns naming what a species eats (e.g. algae, grasses, sap, etc.).

No Comments

No Known Activations