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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     múltiples
    0.55
     An
    0.54
    ino
    0.54
    íduos
    0.53
     harms
    0.53
     lectores
    0.52
    ede
    0.51
     खोले
    0.48
     negras
    0.48
     múltiplos
    0.48
    POSITIVE LOGITS
    ろ
    0.48
    אל
    0.46
    Bạn
    0.44
    אס
    0.43
    צ
    0.43
    Vr
    0.42
    פ
    0.42
    Описание
    0.41
    רה
    0.41
    Een
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.