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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ó
    0.49
    פל
    0.46
     übers
    0.46
    hews
    0.46
    حت
    0.45
    yta
    0.45
    uger
    0.44
    aisen
    0.43
     طالب
    0.43
     ì
    0.43
    POSITIVE LOGITS
     культура
    0.40
    धित
    0.40
    绊
    0.39
    TP
    0.38
     wasted
    0.38
     keterampilan
    0.38
    وها
    0.37
    र
    0.37
     waveguides
    0.36
     rugged
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.