INDEX

Explanations

devices, systems, networks

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

compound nouns or technical terms, particularly multi-word phrases that name specific systems, devices, organizations, or scientific concepts.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron strongly activates on specialized technical and product‐related nouns (e.g., device names, protein names, business or vehicle types).

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

 different

-1.82

 various

-1.55

his

-1.53

 مختلف

-1.46

 varias

-1.46

 विभिन्न

-1.45

carus

-1.40

 различни

-1.39

greja

-1.37

 forskellige

-1.34

POSITIVE LOGITS

1.45

1.30

从来没有

1.27

1.26

 krijgt

1.22

 krijg

1.21

かう

1.20

tial

1.13

整个人

1.11

见了

1.11

Activations Density 0.224%

devices, systems, networks

compound nouns or technical terms, particularly multi-word phrases that name specific systems, devices, organizations, or scientific concepts.

The neuron strongly activates on specialized technical and product‐related nouns (e.g., device names, protein names, business or vehicle types).

No Comments

No Known Activations

devices, systems, networks

compound nouns or technical terms, particularly multi-word phrases that name specific systems, devices, organizations, or scientific concepts.

The neuron strongly activates on specialized technical and product‐related nouns (e.g., device names, protein names, business or vehicle types).

No Comments

No Known Activations