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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ン
    1.10
     duality
    0.97
    ރ
    0.93
     мали
    0.91
    昔
    0.91
     desember
    0.88
     mục
    0.88
     loudspeaker
    0.88
     jolly
    0.88
    //*
    0.87
    POSITIVE LOGITS
     spliced
    1.05
    ب
    1.04
    est
    1.02
    𝐞
    0.98
    notin
    0.96
    iex
    0.95
    yı
    0.95
    broken
    0.94
     scra
    0.92
    nota
    0.90
    Act Density 0.080%

    No Known Activations