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

    Neuronpedia

    INDEX
    Explanations

    Technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rap
    -0.07
     rabbits
    -0.07
     Thủ
    -0.06
    餐
    -0.06
     thereby
    -0.06
    етич
    -0.06
     vá
    -0.06
     прямо
    -0.06
    Tcp
    -0.06
    ู่
    -0.06
    POSITIVE LOGITS
    keyboard
    0.07
    -images
    0.07
    |max
    0.06
     sadd
    0.06
     partager
    0.06
     nebu
    0.06
    人物
    0.06
     Unauthorized
    0.06
     AsyncCallback
    0.06
     приз
    0.06
    Act Density 0.376%

    No Known Activations