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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    kloped
    -0.65
     esternos
    -0.62
    MLLoader
    -0.60
     صوتيه
    -0.60
    ulemon
    -0.59
     الرياضيه
    -0.59
    gameserver
    -0.58
     فريبيس
    -0.58
    tagHelperRunner
    -0.57
     Administrativna
    -0.57
    POSITIVE LOGITS
    s
    0.93
    <bos>
    0.56
    ’
    0.45
     “
    0.44
    runOnUiThread
    0.44
     ‘
    0.44
     MULTI
    0.40
    PATCH
    0.40
    irre
    0.40
     Gallagher
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.