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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ların
    3.48
    ных
    2.95
    nya
    2.78
    larını
    2.78
    요
    2.73
    ları
    2.64
    ről
    2.64
    ные
    2.61
    ました
    2.56
    larının
    2.55
    POSITIVE LOGITS
    as
    2.55
    at
    2.09
    is
    2.09
     quidem
    2.02
    끔
    1.95
    et
    1.93
    ية
    1.93
    athers
    1.91
    perluan
    1.91
     তবে
    1.88
    Act Density 0.072%

    No Known Activations