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

    Neuronpedia

    INDEX
    Explanations

    Alignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Inventory
    -0.06
     Tits
    -0.06
    .week
    -0.06
    DrawerToggle
    -0.06
    PropertyDescriptor
    -0.06
     церк
    -0.06
    -plugins
    -0.06
     publish
    -0.06
     cm
    -0.06
     psy
    -0.06
    POSITIVE LOGITS
    则
    0.07
    ！！
    0.07
    DONE
    0.07
    텔
    0.06
    (...
    0.06
    押
    0.06
     гаран
    0.06
    险
    0.06
    不断
    0.06
    webElement
    0.06
    Act Density 0.002%

    No Known Activations