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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ാനും
    0.64
    abbat
    0.64
     слабы
    0.64
     వైర
    0.63
    ymo
    0.63
    urri
    0.63
     fija
    0.61
    ppers
    0.60
    osto
    0.60
    imentos
    0.60
    POSITIVE LOGITS
     other
    0.71
     this
    0.66
     tarafından
    0.58
                                   
    0.57
    经常
    0.56
     Mats
    0.55
    에
    0.55
     the
    0.55
    其他的
    0.55
     sendiri
    0.55
    Act Density 1.073%

    No Known Activations