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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     eloku
    0.55
     necesitas
    0.55
     saisir
    0.54
    produkt
    0.53
     despised
    0.53
    ebilir
    0.52
    ும்
    0.52
    oğlu
    0.52
    größe
    0.52
     sprinkles
    0.51
    POSITIVE LOGITS
    r
    0.72
    ng
    0.57
    н
    0.56
    and
    0.56
    re
    0.54
    m
    0.53
    ー
    0.53
    on
    0.51
    ../
    0.51
    Type
    0.50
    Act Density 0.005%

    No Known Activations