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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    >
    1.11
    有趣
    1.06
    ¿
    1.03
    ch
    0.99
    ñ
    0.99
    ?}",
    0.98
    ास
    0.95
    $
    0.92
     préd
    0.90
    $.
    0.89
    POSITIVE LOGITS
     Lancet
    1.43
     Incluso
    1.35
     tambah
    1.34
    newlines
    1.34
     degenerative
    1.33
    പ്പെടെ
    1.28
     sekitar
    1.26
    enediamine
    1.26
     Europeo
    1.26
     contrario
    1.25
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.