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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.88
     swallow
    0.81
    1
    0.79
     p
    0.79
    3
    0.77
    4
    0.77
    vier
    0.75
     [
    0.74
     software
    0.74
     sever
    0.71
    POSITIVE LOGITS
     દ્વારા
    1.23
     हानिकारक
    1.19
    ഓം
    1.18
     campañas
    1.15
    forKey
    1.13
     sfai
    1.12
     находится
    1.12
    ᕋ
    1.11
    <unused2176>
    1.11
    Э
    1.11
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.