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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     empiezan
    0.95
     agregó
    0.93
     சேர்த்து
    0.92
    𒋢
    0.90
     comienzan
    0.90
    offe
    0.90
    ärte
    0.89
    riminating
    0.89
     pasando
    0.89
     conlleva
    0.89
    POSITIVE LOGITS
    I
    0.92
    攷
    0.84
    r
    0.81
    Y
    0.78
     것입니다
    0.78
     derailed
    0.77
    n
    0.77
    વાહી
    0.76
    A
    0.75
     my
    0.75
    Act Density 0.001%

    No Known Activations