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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    y
    0.77
    a
    0.76
    in
    0.70
    on
    0.69
    an
    0.64
    er
    0.64
    e
    0.64
    o
    0.62
    u
    0.62
    r
    0.62
    POSITIVE LOGITS
    anning
    0.76
    İ
    0.75
    Б
    0.75
    HT
    0.72
    ANT
    0.72
    Arquivo
    0.71
    Ц
    0.71
    এবং
    0.70
    uidado
    0.70
    ۴
    0.70
    Act Density 0.901%

    No Known Activations