INDEX

Explanations

method calls

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

the dot/period character used for method calls or property access in programming code.

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

This neuron fires on identifiers used as members in “dot” (.) accesses—i.e. property or method names following a period.

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

</u>

-2.63

要知道

-2.22

 According

-2.13

.........

-2.11

ations

-2.11

 Both

-2.09

—

-2.09

If

-2.09

....

-2.06

ный

-2.05

POSITIVE LOGITS

</h2>

2.97

雠

2.91

🧌

2.59

ſelves

2.47

祧

2.44

 étendue

2.41

 delicada

2.39

英寸

2.31

疳

2.31

讎

2.30

Activations Density 0.173%

method calls

the dot/period character used for method calls or property access in programming code.

This neuron fires on identifiers used as members in “dot” (.) accesses—i.e. property or method names following a period.

No Comments

No Known Activations

method calls

the dot/period character used for method calls or property access in programming code.

This neuron fires on identifiers used as members in “dot” (.) accesses—i.e. property or method names following a period.

No Comments

No Known Activations