INDEX

Explanations

SQL varchar data types

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

the word "varchar" in database schema definitions and technical documentation.

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

The neuron fires strongly on domain-specific “format” and code-oriented keywords (e.g. 数据格式, varchar, unexposed, xrange, envisage) – in other words, it picks out specialized technical/jargon tokens.

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

ſſen

-2.95



-2.75

༷

-2.45

ৢ

-2.41

檍

-2.39

笵

-2.38

𓆏

-2.38

玙

-2.38

 semelh

-2.38

”—

-2.38

POSITIVE LOGITS

2.86

2.64

of

2.41

2.34

st

2.31

：

2.30

 indicative

2.28

….

2.22

各样的

2.22

Activations Density 0.005%

SQL varchar data types

the word "varchar" in database schema definitions and technical documentation.

The neuron fires strongly on domain-specific “format” and code-oriented keywords (e.g. 数据格式, varchar, unexposed, xrange, envisage) – in other words, it picks out specialized technical/jargon tokens.

No Comments

No Known Activations

SQL varchar data types

the word "varchar" in database schema definitions and technical documentation.

The neuron fires strongly on domain-specific “format” and code-oriented keywords (e.g. 数据格式, varchar, unexposed, xrange, envisage) – in other words, it picks out specialized technical/jargon tokens.

No Comments

No Known Activations