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

    Neuronpedia

    INDEX
    Explanations

    administrative tasks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    支配
    -0.08
    ological
    -0.07
     behold
    -0.07
    包括
    -0.07
     Asia
    -0.07
    LICENSE
    -0.07
     .↵↵↵↵
    -0.06
     disclosed
    -0.06
     Splash
    -0.06
     HttpSession
    -0.06
    POSITIVE LOGITS
     adverts
    0.07
     tackled
    0.07
    reas
    0.07
    rés
    0.07
     Docs
    0.07
     radix
    0.07
     заказ
    0.06
    Decorator
    0.06
    UAGE
    0.06
    avourites
    0.06
    Act Density 0.178%

    No Known Activations