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

    Neuronpedia

    INDEX
    Explanations

    foreign languages or scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     komple
    0.55
     Nok
    0.53
     Sund
    0.52
     vores
    0.51
     sund
    0.50
     poro
    0.50
     intolerable
    0.49
    oC
    0.49
     Dris
    0.49
     Vort
    0.48
    POSITIVE LOGITS
    وا
    0.73
    У
    0.71
    ک
    0.68
    ע
    0.67
    گ
    0.66
    इ
    0.65
    ع
    0.64
    А
    0.64
    ？
    0.64
    من
    0.63
    Act Density 0.000%

    No Known Activations