INDEX

Explanations

type definitions

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

the word "type" in JSON schemas and structured data definitions.

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

This neuron detects JSON Schema/ API schema declaration keywords (like “type”, “properties”, “items”, “enum”, “default”, 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

-1.26

使った

-1.20

を追加

-1.16

 welchem

-1.13

альных

-1.13

って何

-1.12

-1.11

 november

-1.10

lização

-1.10

relser

-1.09

POSITIVE LOGITS

in

1.41

at

1.41

1.36

 sebuah

1.26

 seorang

1.21

as

1.20

an

1.17

Nicaragua

1.13

Tämä

1.13

 тях

1.13

Activations Density 0.052%

type definitions

the word "type" in JSON schemas and structured data definitions.

This neuron detects JSON Schema/ API schema declaration keywords (like “type”, “properties”, “items”, “enum”, “default”, etc.).

No Comments

No Known Activations

type definitions

the word "type" in JSON schemas and structured data definitions.

This neuron detects JSON Schema/ API schema declaration keywords (like “type”, “properties”, “items”, “enum”, “default”, etc.).

No Comments

No Known Activations