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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     From
    0.77
     To
    0.77
    عهد
    0.76
     चाहते
    0.74
     For
    0.73
    ->"
    0.72
     know
    0.71
     manter
    0.70
    --)
    0.70
    Required
    0.70
    POSITIVE LOGITS
     अर
    0.94
    Kok
    0.93
    ﻱ
    0.89
    sag
    0.89
     počas
    0.88
    耍
    0.88
     convolutions
    0.88
    owlapi
    0.88
     ਨੇ
    0.87
    sø
    0.87
    Act Density 0.000%

    No Known Activations