INDEX

Explanations

JOIN clauses

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

SQL JOIN conditions, particularly the ON clause with equality comparisons between table columns.

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

The neuron activates on SQL join conditions, especially the “ON” keyword and associated comparisons (equals signs, ANDs) in JOIN clauses.

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

any

-1.59

</em>

-1.57

yet

-1.35

too

-1.30

or

-1.23

ద్

-1.21

but

-1.20

 потеря

-1.20

 even

-1.19

</strong>

-1.18

POSITIVE LOGITS

Ꮫ

1.68

 pittore

1.64

 übrigen

1.47

心想

1.45

 africains

1.39

 signore

1.38

撬

1.37

莚

1.36

橚

1.36

 lusso

1.32

Activations Density 0.020%

JOIN clauses

SQL JOIN conditions, particularly the ON clause with equality comparisons between table columns.

The neuron activates on SQL join conditions, especially the “ON” keyword and associated comparisons (equals signs, ANDs) in JOIN clauses.

No Comments

No Known Activations

JOIN clauses

SQL JOIN conditions, particularly the ON clause with equality comparisons between table columns.

The neuron activates on SQL join conditions, especially the “ON” keyword and associated comparisons (equals signs, ANDs) in JOIN clauses.

No Comments

No Known Activations