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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sust
    -0.07
     insists
    -0.07
    agh
    -0.07
    rij
    -0.07
     scept
    -0.06
     criticised
    -0.06
    िसम
    -0.06
     vouchers
    -0.06
    hope
    -0.06
     куль
    -0.06
    POSITIVE LOGITS
    要
    0.07
    ♠
    0.07
     owning
    0.07
    会
    0.06
    べき
    0.06
     to
    0.06
    ことを
    0.06
    สามารถ
    0.06
     능
    0.06
     تعریف
    0.06
    Act Density 0.027%

    No Known Activations