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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ambassador
    -0.07
    員
    -0.06
    ()">↵
    -0.06
     disclosed
    -0.06
    unidad
    -0.06
    旋
    -0.06
    عاد
    -0.06
    将
    -0.06
    ilha
    -0.06
    Stuff
    -0.06
    POSITIVE LOGITS
     ngang
    0.07
    (selection
    0.06
     vy
    0.06
     diagram
    0.06
    Vk
    0.06
     DriverManager
    0.06
    738
    0.06
    ��이지
    0.06
    997
    0.06
    ackets
    0.06
    Act Density 0.000%

    No Known Activations