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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Также
    0.85
     кілька
    0.81
     autoridades
    0.79
     важное
    0.78
     несколько
    0.78
    😆
    0.77
     самую
    0.75
    枧
    0.75
     anche
    0.75
     даже
    0.75
    POSITIVE LOGITS
    ph
    0.71
    ls
    0.68
    ol
    0.68
    d
    0.68
     envisage
    0.68
    ود
    0.67
    nd
    0.66
    መሳሳይ
    0.66
    cre
    0.65
    faces
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.