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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     дней
    1.08
    ໍ່
    0.90
    лым
    0.82
     receb
    0.82
    tmux
    0.80
    insuku
    0.79
     φορ
    0.79
    椑
    0.79
     akhir
    0.78
     tokoh
    0.77
    POSITIVE LOGITS
     library
    0.65
    un
    0.63
    ia
    0.61
    ig
    0.60
    Re
    0.57
    ţi
    0.57
    ature
    0.56
     fc
    0.56
    uret
    0.55
    FC
    0.55
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.