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

    Neuronpedia

    INDEX
    Explanations

    undercover stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mixing
    -0.07
    osis
    -0.07
    osu
    -0.07
    Balance
    -0.06
     jump
    -0.06
    wayne
    -0.06
     dumped
    -0.06
     오늘
    -0.06
     состав
    -0.06
    иться
    -0.06
    POSITIVE LOGITS
     آی
    0.07
    ：<
    0.06
    ">{
    0.06
     mesure
    0.06
    ولد
    0.06
    NSBundle
    0.06
     Společ
    0.06
    _pas
    0.06
    (Route
    0.06
    );

↵
    0.06
    Act Density 0.019%

    No Known Activations