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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OCD
    -0.07
     RUNNING
    -0.07
     arşiv
    -0.06
     Harden
    -0.06
     dirname
    -0.06
    -zA
    -0.06
    дет
    -0.06
     Abdul
    -0.06
    ="__
    -0.06
    editary
    -0.05
    POSITIVE LOGITS
     Torrent
    0.07
    ataire
    0.07
    ños
    0.07
    架
    0.06
    キ
    0.06
    vido
    0.06
    ')+
    0.06
     Contributor
    0.06
     WWW
    0.06
    πτωση
    0.06
    Act Density 0.002%

    No Known Activations