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

    Neuronpedia

    INDEX
    Explanations

    words related to legality and business, particularly about not hiring

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oprot
    -0.68
     esternos
    -0.66
    EDEFAULT
    -0.63
     InputDecoration
    -0.63
     "..\..\
    -0.62
    styleType
    -0.62
    setVerticalGroup
    -0.60
    migrationBuilder
    -0.58
    astéroïdes
    -0.57
    UseVisualStyle
    -0.54
    POSITIVE LOGITS
     Lordships
    0.53
    arrol
    0.50
    nics
    0.49
     myſelf
    0.49
    haustible
    0.49
    Instru
    0.47
    ftances
    0.47
     Majefty
    0.47
    wiſe
    0.47
    leſs
    0.46
    Act Density 1.882%

    No Known Activations