INDEX

Explanations

web posts

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

the word "post" in programming contexts, particularly in code related to HTTP POST requests or post-related variables.

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

This neuron detects uses of the HTTP‐request verbs “get” and “post” (e.g. function names, variables, or form methods).

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

my

-1.55

was

-1.45

-1.38

ひと

-1.38

-1.37

</u>

-1.34

calça

-1.34

小さな

-1.33

-1.31

de

-1.29

POSITIVE LOGITS

Previously

1.48

ogyn

1.47

Odpovědět

1.46

 which

1.45

où

1.44

鷙

1.44

 Ако

1.41

貲

1.41

We

1.39

 ندار

1.39

Activations Density 0.001%

web posts

the word "post" in programming contexts, particularly in code related to HTTP POST requests or post-related variables.

This neuron detects uses of the HTTP‐request verbs “get” and “post” (e.g. function names, variables, or form methods).

No Comments

No Known Activations

web posts

the word "post" in programming contexts, particularly in code related to HTTP POST requests or post-related variables.

This neuron detects uses of the HTTP‐request verbs “get” and “post” (e.g. function names, variables, or form methods).

No Comments

No Known Activations