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

    Neuronpedia

    INDEX
    Explanations

    variables related to statistical methods and model evaluation

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

    frequency or rarity of events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auguri
    -0.46
    VersionUID
    -0.46
     mittlerweile
    -0.35
    most
    -0.35
    équi
    -0.35
     puesta
    -0.33
     entgegen
    -0.33
     again
    -0.33
    HasForeignKey
    -0.33
     casado
    -0.33
    POSITIVE LOGITS
    الحياه
    0.61
    OGND
    0.47
    MeasureSpec
    0.45
     detailsNormal
    0.44
    RTEE
    0.44
    tagez
    0.43
    orteur
    0.43
    lusconi
    0.43
    waitKey
    0.43
    becker
    0.43
    Act Density 0.144%

    No Known Activations