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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     देखील
    1.33
    हरु
    1.26
     diatas
    1.22
     सुद्धा
    1.21
    無い
    1.18
     welches
    1.17
    の為
    1.16
    繋
    1.15
     dibawah
    1.14
     الغير
    1.14
    POSITIVE LOGITS
    —
    1.16
     nong
    0.92
    .—
    0.89
     etcétera
    0.88
    たとえば
    0.79
     nonresident
    0.78
    9
    0.77
     nond
    0.75
    --
    0.74
     nonfiction
    0.74
    Act Density 0.208%

    No Known Activations