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

    Neuronpedia

    INDEX
    Explanations

    recommendations and best practices regarding code usage

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

    recommended practices and ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.84
     للمعارف
    -0.79
    oa̍t
    -0.77
    ImageContext
    -0.77
     Chwiliwch
    -0.74
     IBOutlet
    -0.73
     المعيارى
    -0.73
     CURIAM
    -0.72
    AndEndTag
    -0.69
    RotationOrder
    -0.69
    POSITIVE LOGITS
    OfClass
    0.33
     responsabilité
    0.32
     habitudes
    0.31
    wohnungen
    0.31
     always
    0.31
     sempre
    0.31
    Always
    0.31
    always
    0.29
    use
    0.29
    warning
    0.28
    Act Density 0.246%

    No Known Activations