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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    头顶
    -0.07
     위하여
    -0.07
     OCD
    -0.07
    -induced
    -0.06
     ADHD
    -0.06
    为期
    -0.06
     רחוק
    -0.06
    殍
    -0.06
    -p
    -0.06
     layered
    -0.06
    POSITIVE LOGITS
    (worker
    0.07
    مؤلف
    0.07
    ЛО
    0.06
    arine
    0.06
     getIntent
    0.06
    זרים
    0.06
    .Art
    0.06
    姬
    0.06
    这些人
    0.06
     MSC
    0.06
    Act Density 0.091%

    No Known Activations