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

    Neuronpedia

    INDEX
    Explanations

    EP

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cresc
    -0.07
    人員
    -0.07
    .Fetch
    -0.07
    [max
    -0.07
    (person
    -0.07
    (test
    -0.07
    ([
    -0.06
    reverse
    -0.06
    ziej
    -0.06
     Orch
    -0.06
    POSITIVE LOGITS
    拼多多
    0.08
    之乡
    0.07
     marketplace
    0.07
    SharedPtr
    0.07
    érica
    0.07
    飞船
    0.07
     ليبيا
    0.06
    传媒
    0.06
    遇难
    0.06
     fellowship
    0.06
    Act Density 0.003%

    No Known Activations