INDEX

Explanations

object identifiers

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

the string "oid" (object identifier) in technical/database contexts.

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

The neuron fires on identifier tokens related to object or record IDs (e.g. “ObjectId,” “oid,” “id,” “object_id”).

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

↵↵

-3.47

怍

-2.34

to

-2.08

 nods

-2.02

</b>

-1.94

 have

-1.92

-1.88

 portion

-1.86

."

-1.85

-1.84

POSITIVE LOGITS

3.27

 Autó

2.39

뻣

2.28

釭

2.22

 terminó

2.08

 Periode

1.98

葑

1.96

 สำหรับ

1.95

 برای

1.93

 Spanyol

1.93

Activations Density 0.001%

object identifiers

the string "oid" (object identifier) in technical/database contexts.

The neuron fires on identifier tokens related to object or record IDs (e.g. “ObjectId,” “oid,” “id,” “object_id”).

No Comments

No Known Activations

object identifiers

the string "oid" (object identifier) in technical/database contexts.

The neuron fires on identifier tokens related to object or record IDs (e.g. “ObjectId,” “oid,” “id,” “object_id”).

No Comments

No Known Activations