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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     আহত
    0.60
     anderes
    0.59
     связаны
    0.58
     dienen
    0.57
     bitOp
    0.57
    влено
    0.57
     niemals
    0.57
     afecta
    0.56
     Schad
    0.56
     direkte
    0.55
    POSITIVE LOGITS
     AFC
    0.72
    ☆☆
    0.72
     ومن
    0.69
     Ρ
    0.69
     وقتی
    0.68
    yar
    0.66
     Onc
    0.66
     Great
    0.65
     previous
    0.64
     Railways
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.