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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ות
    1.61
    ব
    1.59
    𝗳
    1.55
    leine
    1.55
    𝘳
    1.54
    ქმედ
    1.51
    अ
    1.51
    jų
    1.50
     intang
    1.48
    ניים
    1.48
    POSITIVE LOGITS
     зі
    1.84
     громадян
    1.74
     собра
    1.71
     государства
    1.69
    ين
    1.68
    Рис
    1.66
    wipe
    1.63
     bulunan
    1.63
     сам
    1.58
     импера
    1.55
    Act Density 0.000%

    No Known Activations