INDEX

Explanations

zombies, undead, necromancer, death

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

terms related to death, corpses, zombies, and the undead.

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

The neuron detects words referring to death, decay, corpses, and undead themes.

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

 позволяет

-1.68

えっ

-1.65

歟

-1.60

().

-1.58

そも

-1.51

すごく

-1.50

看似

-1.50

欤

-1.41

いますが

-1.41

().

-1.41

POSITIVE LOGITS

星

1.42

’

1.42

чя

1.33

𝐆

1.24

近年来

1.22

ünd

1.20

𝐒

1.20

 nite

1.19

get

1.17

写真

1.16

Activations Density 0.047%

zombies, undead, necromancer, death

terms related to death, corpses, zombies, and the undead.

The neuron detects words referring to death, decay, corpses, and undead themes.

No Comments

No Known Activations

zombies, undead, necromancer, death

terms related to death, corpses, zombies, and the undead.

The neuron detects words referring to death, decay, corpses, and undead themes.

No Comments

No Known Activations