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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    র
    0.87
    י
    0.75
     iliş
    0.75
     impass
    0.75
     atk
    0.74
     өчен
    0.73
     Critics
    0.73
    তে
    0.71
     ihe
    0.71
    etään
    0.71
    POSITIVE LOGITS
    ab
    0.70
     Shreve
    0.70
     waveforms
    0.68
     rechter
    0.68
    듬
    0.66
    it
    0.65
    to
    0.65
    additional
    0.65
    全都
    0.63
    equations
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.