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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ed
    0.87
    owanej
    0.81
    лы
    0.78
    atlar
    0.75
    GOING
    0.75
    isolated
    0.74
    aar
    0.73
    er
    0.72
    uy
    0.70
    owanym
    0.70
    POSITIVE LOGITS
    સ
    0.81
     fatalities
    0.79
     casualties
    0.79
     mobilier
    0.78
    全
    0.76
    敉
    0.75
     favor
    0.74
     casualty
    0.74
    ກ
    0.73
     facilité
    0.72
    Act Density 0.006%

    No Known Activations