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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    o
    0.80
    el
    0.78
    u
    0.78
    uuid
    0.76
    al
    0.74
    uia
    0.73
    er
    0.73
    a
    0.71
    rasp
    0.71
    os
    0.71
    POSITIVE LOGITS
     hingegen
    0.81
     저는
    0.80
    См
    0.77
    저는
    0.77
     უფრო
    0.76
    璈
    0.75
     პარ
    0.73
     массы
    0.73
    职责
    0.72
     člán
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.