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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     encuentren
    0.66
    maal
    0.65
     acestea
    0.63
     ৫৭
    0.61
     услови
    0.59
     ámbito
    0.59
     όπως
    0.58
    ീയ
    0.58
     atât
    0.58
     オ
    0.58
    POSITIVE LOGITS
    as
    1.18
    er
    1.18
    quela
    1.08
    ת
    1.07
    ة
    1.07
    ed
    1.02
    ার
    1.02
    an
    0.90
    en
    0.90
    in
    0.88
    Act Density 0.371%

    No Known Activations