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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Depression
    0.91
     Dipl
    0.90
     प्रया
    0.89
     through
    0.87
    !
    0.86
     Life
    0.85
     pensioner
    0.85
     halted
    0.84
     Bahamas
    0.84
     Metabolic
    0.84
    POSITIVE LOGITS
    を使う
    1.13
    '])->
    1.03
    '])[
    1.02
     codimension
    1.02
    爣
    1.00
     संदर्भित
    0.98
     Verhältnis
    0.98
    었던
    0.97
    かの
    0.96
    binom
    0.96
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.