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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     artériel
    0.86
    NAME
    0.77
    包装
    0.76
    Bien
    0.76
     rilas
    0.75
    SHRI
    0.75
    潜在
    0.75
    து
    0.75
    攻击
    0.75
    僚
    0.75
    POSITIVE LOGITS
    sion
    0.89
     (
    0.76
    師
    0.74
    sg
    0.73
    sley
    0.73
    iol
    0.72
    sp
    0.71
    yt
    0.71
    randomIndex
    0.70
    yesi
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.