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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ጨም
    0.67
    ﻤ
    0.65
    َب
    0.61
    UNCIL
    0.61
    ﺎ
    0.59
     Еўро
    0.58
    𝘁
    0.58
     таксама
    0.57
     상당히
    0.57
     కూడా
    0.56
    POSITIVE LOGITS
     which
    0.71
     or
    0.66
    -
    0.64
     when
    0.63
     its
    0.63
     quando
    0.61
     versus
    0.60
     vaya
    0.59
     the
    0.59
     cuando
    0.58
    Act Density 0.295%

    No Known Activations