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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     there
    0.73
     Misalnya
    0.66
     careless
    0.65
     Nagpur
    0.63
     tenha
    0.62
     There
    0.61
     MNIST
    0.60
     Lorem
    0.58
     ovaries
    0.58
     P
    0.58
    POSITIVE LOGITS
    是一种
    0.95
    пуляр
    0.95
     multipurpose
    0.93
    是一種
    0.89
    小型
    0.84
     multifunctional
    0.82
     populaire
    0.81
     популяр
    0.80
     customizable
    0.77
    一種
    0.77
    Act Density 1.688%

    No Known Activations