Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specialized nouns and important technical or domain-specific terms across various contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @gersonkroiz

    questions and requests related to coding, definitions, or names of specific concepts.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    multiple languages foreign terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     .
    0.10
    ↵
    0.10
    ()
    0.10
    [
    0.10
     \
    0.10
     {
    0.10
    <0x0D>
    0.09
     [
    0.09
    \
    0.09
     。
    0.09
    POSITIVE LOGITS
    पीरियंस
    0.11
    ätzung
    0.09
     záb
    0.09
    heiz
    0.09
    SrvGroup
    0.08
    യില്ല
    0.08
     жизнь
    0.08
     Gesundheit
    0.08
     ಒಳಗ
    0.08
    verständ
    0.08
    Act Density 0.001%

    No Known Activations