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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    да
    0.72
    (
    0.72
    าม
    0.70
    Conj
    0.70
    นี้
    0.70
    ,
    0.70
    ק
    0.67
    soever
    0.66
    d
    0.66
    Etiam
    0.64
    POSITIVE LOGITS
    મેટ
    0.86
     ப்
    0.82
     Mitglied
    0.80
     Việt
    0.77
     solicitud
    0.75
     tendrás
    0.75
     patří
    0.74
     vantaggio
    0.73
    পরিচিত
    0.73
     Advantages
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.