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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ar
    1.09
    Classic
    0.84
    あれ
    0.77
    er
    0.75
    See
    0.73
     dile
    0.71
     Plane
    0.70
    Hector
    0.69
    Independent
    0.68
     Classic
    0.66
    POSITIVE LOGITS
    蚪
    0.81
     которые
    0.78
    ugar
    0.77
    laş
    0.76
     участка
    0.76
    энне
    0.76
    вается
    0.75
     jugado
    0.75
     Старки
    0.74
    ровая
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.