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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     those
    -1.13
     considerably
    -1.09
     unparalleled
    -1.08
     commonly
    -1.02
     on
    -1.02
     with
    -1.01
    ・・。
    -1.00
     steadily
    -0.97
     one
    -0.96
     superbly
    -0.96
    POSITIVE LOGITS
     boister
    1.05
     possibilités
    1.02
     _________
    1.00
     ferocious
    0.97
    vidéo
    0.96
     ______
    0.96
    <em>
    0.95
    nthesis
    0.95
    鮒
    0.94
     specif
    0.94
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.