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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ar
    0.77
    an
    0.72
    ol
    0.65
    ab
    0.61
    ap
    0.60
     ဂ
    0.60
    om
    0.60
    ل
    0.59
    ak
    0.58
    ell
    0.58
    POSITIVE LOGITS
    ।
    0.81
    ።
    0.72
    ।”
    0.66
     ।
    0.64
     pihaknya
    0.64
     коронави
    0.63
    ։
    0.63
     tantamount
    0.61
     was
    0.60
     is
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.