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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     عر
    0.50
     پن
    0.49
    <unused1023>
    0.49
     لوبوي
    0.48
    OUIS
    0.45
     испыта
    0.45
     ಹಿ
    0.44
     duckys
    0.44
    <unused968>
    0.44
     해결
    0.44
    POSITIVE LOGITS
     switch
    0.46
    3
    0.46
    mes
    0.46
    1
    0.45
    zam
    0.43
    zur
    0.42
     system
    0.41
    я
    0.41
     net
    0.41
    switch
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.