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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    egen
    0.68
     conservatively
    0.67
     jugadores
    0.63
    并不
    0.63
    ëm
    0.61
    hezza
    0.61
     لهذه
    0.61
     organizaciones
    0.61
    ệc
    0.60
     ange
    0.60
    POSITIVE LOGITS
    ো
    0.85
    І
    0.80
    JlcG
    0.77
    בר
    0.76
    २
    0.74
    טי
    0.73
    i
    0.73
    k
    0.71
    נה
    0.71
    ริ
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.