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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     обы
    1.39
    зы
    1.32
     нашем
    1.31
     шести
    1.29
     zwy
    1.28
     писатель
    1.27
    ेलकम
    1.27
    gó
    1.27
     трех
    1.26
    <unused78>
    1.25
    POSITIVE LOGITS
     rounding
    0.92
     and
    0.87
     forms
    0.82
    ovana
    0.82
    veel
    0.81
     sidelines
    0.81
     replacement
    0.80
     more
    0.80
     funded
    0.80
     additional
    0.79
    Act Density 0.000%

    No Known Activations