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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ᏼ
    0.88
     роботу
    0.81
     메서
    0.79
    到一个
    0.79
     pousse
    0.78
    是个
    0.77
     મારા
    0.76
     travaux
    0.76
     मलया
    0.75
    Mình
    0.75
    POSITIVE LOGITS
     Während
    0.74
     During
    0.73
     kaum
    0.71
    anging
    0.70
    ia
    0.70
    ustration
    0.70
     unclaimed
    0.70
    いた
    0.68
     FPR
    0.68
    ópez
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.