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
     theater
    -0.07
    จำ
    -0.07
     SC
    -0.07
     Army
    -0.07
     solder
    -0.07
     دسته
    -0.06
     CP
    -0.06
    playing
    -0.06
     theatre
    -0.06
     gy
    -0.06
    POSITIVE LOGITS
     afterwards
    0.07
    .djangoproject
    0.06
     ettir
    0.06
    /plugin
    0.06
    _WIN
    0.06
     ''){↵
    0.06
     {})↵
    0.06
     ат
    0.06
    真是
    0.06
    <Map
    0.06
    Act Density 0.005%

    No Known Activations