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

    Neuronpedia

    INDEX
    Explanations

    IJ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (it
    -0.07
    DE
    -0.07
    ưỡng
    -0.07
    >A
    -0.07
    avelength
    -0.07
    igg
    -0.06
     Boulder
    -0.06
     barn
    -0.06
    WA
    -0.06
     Rut
    -0.06
    POSITIVE LOGITS
    名
    0.07
     diện
    0.06
    ather
    0.06
    $new
    0.06
    нерг
    0.06
    .PLL
    0.06
     Calc
    0.06
     اما
    0.06
    мор
    0.06
    incer
    0.06
    Act Density 0.002%

    No Known Activations