INDEX

Explanations

occurrence of complications

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

medical terms related to complications in healthcare.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

This neuron detects occurrences of the word “complications,” especially in medical or clinical contexts.

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

-2.67

derdag

-2.48

циях

-2.36

迄

-2.30

蹰

-2.28

It

-2.27

見ても

-2.22

 impone

-2.22

scribers

-2.16

</i>

-2.14

POSITIVE LOGITS

the

3.39

2.81

2.66

幾天

2.56

所以我

2.50

その

2.44

屜

2.44

2.41

Activations Density 0.016%

occurrence of complications

medical terms related to complications in healthcare.

This neuron detects occurrences of the word “complications,” especially in medical or clinical contexts.

No Comments

No Known Activations

occurrence of complications

medical terms related to complications in healthcare.

This neuron detects occurrences of the word “complications,” especially in medical or clinical contexts.

No Comments

No Known Activations