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

    Neuronpedia

    INDEX
    Explanations

    advantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accordingly
    -0.67
    WebControls
    -0.60
    ModelForm
    -0.59
    pfung
    -0.58
     архивлан
    -0.57
    stuffs
    -0.52
    jsxFileName
    -0.52
    vician
    -0.51
    calaure
    -0.50
    ligkeit
    -0.49
    POSITIVE LOGITS
     whoſe
    0.80
     enfans
    0.77
     feroit
    0.69
     normaux
    0.63
     rêves
    0.60
     þat
    0.60
     vítimas
    0.60
     scatola
    0.57
     preuves
    0.57
     prisonniers
    0.57
    Act Density 0.054%

    No Known Activations