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

    Neuronpedia

    INDEX
    Explanations

    plastic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    制造
    -0.07
     получения
    -0.07
    aires
    -0.07
    _CARD
    -0.07
    MAIL
    -0.07
    潮
    -0.06
     gameId
    -0.06
    mailer
    -0.06
    AMED
    -0.06
     Void
    -0.06
    POSITIVE LOGITS
    olumbia
    0.07
    กล
    0.06
    .docker
    0.06
     Roths
    0.06
     Ex
    0.06
     accommod
    0.06
    Receipt
    0.06
    '}↵↵
    0.06
    '''↵↵
    0.06
     Knife
    0.06
    Act Density 0.017%

    No Known Activations