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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     súa
    0.70
     esistono
    0.69
     उनका
    0.69
     svoju
    0.68
     dearest
    0.67
     इसे
    0.66
     svoje
    0.66
     coloro
    0.65
     इसका
    0.64
     disebutkan
    0.64
    POSITIVE LOGITS
     skillful
    0.57
     Eurasian
    0.57
    e
    0.54
    0.54
     careful
    0.52
     भीम
    0.52
     extensive
    0.51
    ExprNode
    0.51
     Balkan
    0.51
     palliative
    0.51
    Act Density 0.165%

    No Known Activations