INDEX

Explanations

animal homes

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

animal habitats and living spaces like nests, dens, burrows, hives, and shelters.

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

The neuron activates on terms denoting animal dwellings or nesting sites (e.g., den, nest, burrow, colony).

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

-1.60

In

-1.52

-1.47

 एवं

-1.46

en

-1.45

and

-1.40

et

-1.38

-1.35

-1.34

POSITIVE LOGITS

 الشاشة

1.60

 oči

1.41

 彼女

1.38

 ellos

1.34

 knitted

1.34

 otras

1.32

 😀

1.32

 ciertas

1.29

 distraught

1.27

 schaff

1.27

Activations Density 0.017%

animal homes

animal habitats and living spaces like nests, dens, burrows, hives, and shelters.

The neuron activates on terms denoting animal dwellings or nesting sites (e.g., den, nest, burrow, colony).

No Comments

No Known Activations

animal homes

animal habitats and living spaces like nests, dens, burrows, hives, and shelters.

The neuron activates on terms denoting animal dwellings or nesting sites (e.g., den, nest, burrow, colony).

No Comments

No Known Activations