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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     on
    0.30
    на
    0.29
    ку
    0.28
    ного
    0.27
     pubblica
    0.25
    ेंट
    0.25
    ر
    0.25
    د
    0.25
    ੇ
    0.25
    taxon
    0.24
    POSITIVE LOGITS
    :
    0.29
    も
    0.29
    ING
    0.27
    {
    0.26
    도
    0.26
    -
    0.25
     be
    0.23
    (
    0.22
     {
    0.22
    :\
    0.21
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.