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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ları
    1.70
    ку
    1.65
    (\
    1.64
    ным
    1.63
    きた
    1.63
     stature
    1.57
    ų
    1.56
    ної
    1.55
    ند
    1.54
    ном
    1.52
    POSITIVE LOGITS
    ്രി
    1.66
     وعند
    1.59
    ीन
    1.54
    folger
    1.51
    ended
    1.50
    ffen
    1.48
     olha
    1.48
    smoothed
    1.46
    ে
    1.44
     aucun
    1.42
    Act Density 0.027%

    No Known Activations