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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Trả
    0.88
    ם
    0.84
    على
    0.77
    ReturnType
    0.76
    त
    0.76
    Как
    0.75
    ف
    0.73
    ක්
    0.73
    Pi
    0.72
    ط
    0.72
    POSITIVE LOGITS
     aerobics
    0.88
     немец
    0.84
     σε
    0.83
     mountaine
    0.83
     blacksmith
    0.80
     nirv
    0.79
     NSR
    0.79
     Berlin
    0.79
     supremac
    0.78
     bootcamp
    0.78
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.