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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ن
    1.70
    ive
    1.10
    न
    1.06
    他の
    0.97
    라
    0.95
     بعنوان
    0.95
    ००
    0.94
    ર
    0.93
    ுக்கு
    0.92
    /
    0.92
    POSITIVE LOGITS
     combating
    1.66
     towering
    1.48
     solvers
    1.45
     መሳሪያ
    1.39
     marching
    1.33
     depressions
    1.32
    getWindow
    1.31
     pollinators
    1.31
     Pogis
    1.31
     solving
    1.30
    Act Density 0.000%

    No Known Activations