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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    телем
    0.90
    igheid
    0.90
    ključ
    0.86
    То
    0.84
    kran
    0.84
    łem
    0.82
    Todas
    0.81
     Ще
    0.81
    ות
    0.80
    Pued
    0.80
    POSITIVE LOGITS
    た
    1.01
    ਤੀ
    0.88
    いきます
    0.88
    o
    0.86
    perger
    0.84
     EBIT
    0.83
    erry
    0.80
    мма
    0.80
     Bhopal
    0.79
     besuchte
    0.78
    Act Density 0.001%

    No Known Activations