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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     الزمن
    0.73
    borg
    0.73
    暄
    0.72
    ysi
    0.71
    iselle
    0.69
     Bên
    0.68
     s
    0.67
     fürs
    0.66
    mp
    0.65
     glist
    0.65
    POSITIVE LOGITS
    мі
    0.84
    ді
    0.81
    स
    0.76
    ственной
    0.75
     Standort
    0.73
    क
    0.73
    体系
    0.72
    ство
    0.71
    단을
    0.71
    ці
    0.70
    Act Density 0.002%

    No Known Activations