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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ');
    0.75
     folgender
    0.71
     Что
    0.70
     Semoga
    0.68
     Quando
    0.68
     Dieses
    0.67
     Schrift
    0.66
     Пусть
    0.66
     Когда
    0.64
     Etc
    0.64
    POSITIVE LOGITS
    ز
    0.58
    direct
    0.50
    sac
    0.49
    water
    0.48
    elev
    0.48
    seller
    0.48
    inhib
    0.48
    scale
    0.47
    та
    0.47
    ከላ
    0.46
    Act Density 0.139%

    No Known Activations