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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     esfor
    0.77
     eficiente
    0.74
     eficiencia
    0.73
     Иногда
    0.73
     torpedo
    0.71
     incol
    0.71
     fatalities
    0.69
     сме
    0.68
    alne
    0.68
     зу
    0.68
    POSITIVE LOGITS
    n
    1.10
    l
    1.09
    g
    1.08
    gün
    1.02
    j
    1.02
    chrotron
    0.96
    可以将
    0.95
    పై
    0.92
    nacht
    0.91
    引领
    0.91
    Act Density 0.007%

    No Known Activations