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

    Neuronpedia

    INDEX
    Explanations

    Apex code questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    敢
    -0.08
     Drawable
    -0.07
     dummy
    -0.07
    -прав
    -0.07
     condemn
    -0.07
     tuning
    -0.07
    Highlight
    -0.07
    ertino
    -0.06
     deviation
    -0.06
    -अ
    -0.06
    POSITIVE LOGITS
    ForegroundColor
    0.07
    ;');↵
    0.06
    ;";↵
    0.06
     mapStateToProps
    0.06
    TypeID
    0.06
     vidéos
    0.06
    .isNotEmpty
    0.06
    ΟΦ
    0.06
    vatel
    0.06
     headquarters
    0.06
    Act Density 0.013%

    No Known Activations