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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tsukuyomi
    -0.81
    EStream
    -0.70
    Origin
    -0.70
     inspir
    -0.69
     Feather
    -0.64
     Severus
    -0.63
    arsity
    -0.62
     difference
    -0.61
    ãĤº
    -0.60
     Donation
    -0.60
    POSITIVE LOGITS
    berman
    0.94
    jo
    0.72
    irements
    0.70
    sur
    0.69
    ija
    0.69
    bern
    0.68
    elected
    0.68
    bers
    0.67
    amus
    0.67
    enough
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.