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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lač
    0.43
     meta
    0.40
    September
    0.39
    にご
    0.39
    ิบ
    0.39
    JAV
    0.38
    ...............
    0.38
     yellow
    0.37
    สอบ
    0.37
     ২০১৭
    0.37
    POSITIVE LOGITS
     remplacement
    0.50
     //-
    0.45
    㑔
    0.44
    établir
    0.44
    hitungan
    0.43
     прият
    0.42
     흥
    0.41
     udara
    0.40
     commandBuffer
    0.40
     njihov
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.