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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Trump
    -0.07
     KM
    -0.07
    出去
    -0.07
    zzle
    -0.06
     dumped
    -0.06
    ايت
    -0.06
     indul
    -0.06
     Fourier
    -0.06
    istically
    -0.06
    .GPIO
    -0.06
    POSITIVE LOGITS
    orias
    0.07
    (curr
    0.07
    setColor
    0.07
     cdecl
    0.06
     VAN
    0.06
    documento
    0.06
    /window
    0.06
     Amen
    0.06
    /ss
    0.06
    wel
    0.06
    Act Density 0.036%

    No Known Activations