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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    پ
    0.48
    ﻤ
    0.45
    يف
    0.44
    バ
    0.43
    三分
    0.43
    ４
    0.43
    نيف
    0.41
     يف
    0.40
    ３
    0.40
    beatCounter
    0.40
    POSITIVE LOGITS
     Airbnb
    0.45
    uk
    0.41
    an
    0.40
     NOx
    0.39
    ik
    0.38
     Dropbox
    0.38
     Realtor
    0.38
    ar
    0.38
     Godzilla
    0.38
    u
    0.37
    Act Density 3.939%

    No Known Activations