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

    Neuronpedia

    INDEX
    Explanations

    statements that begin with or emphasize "overall."

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

    "overall" and related summaries

    np_acts-logits-general · gemini-2.0-flash

    general assessments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HttpNotFound
    -0.69
     punishable
    -0.59
     precisely
    -0.58
     Voit
    -0.58
     précisément
    -0.57
    sekret
    -0.56
     procedentes
    -0.55
    tears
    -0.55
    o
    -0.54
    اتي
    -0.54
    POSITIVE LOGITS
    OVERALL
    0.91
     geral
    0.76
     generale
    0.71
    UnknownFieldSet
    0.70
     keseluruhan
    0.70
    XMLSchema
    0.69
    overall
    0.68
    batore
    0.68
    LikeLike
    0.67
     Overall
    0.67
    Act Density 0.112%

    No Known Activations