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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     habíamos
    1.01
    m
    1.01
     sabía
    0.96
    ायचे
    0.94
    MeToo
    0.92
     Europeo
    0.91
     fatorial
    0.91
     podríamos
    0.87
     strangled
    0.87
    م
    0.87
    POSITIVE LOGITS
    相同的
    0.93
    ानंद
    0.91
    satisf
    0.84
    同样的
    0.83
    正常的
    0.82
     satisfactory
    0.81
    venida
    0.79
     ample
    0.77
    ável
    0.76
    ரத்தில்
    0.75
    Act Density 2.295%

    No Known Activations