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

    Neuronpedia

    INDEX
    Explanations

    Set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    principalTable
    -0.56
    ith
    -0.52
    On
    -0.51
    ionais
    -0.50
    wness
    -0.50
     ON
    -0.47
     оно
    -0.47
     degradability
    -0.46
    eczki
    -0.45
    ever
    -0.45
    POSITIVE LOGITS
    AutoScaleMode
    0.70
    NUMX
    0.69
    board
    0.61
    te
    0.59
    Enllaços
    0.59
     Erişim
    0.54
     Dostupné
    0.54
    questa
    0.53
    teig
    0.53
    tling
    0.53
    Act Density 0.079%

    No Known Activations