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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    B
    0.64
     loin
    0.63
     annual
    0.62
    +"\
    0.59
    स्त्रा
    0.59
     annually
    0.58
    动物
    0.57
    াগ
    0.57
    ']+
    0.57
    ți
    0.56
    POSITIVE LOGITS
     మహ
    0.82
    し
    0.79
    ushing
    0.78
     порядке
    0.77
     бывают
    0.77
     erano
    0.77
     vidhan
    0.75
     tinham
    0.75
    indelijk
    0.75
     आखिरकार
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.