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

    Neuronpedia

    INDEX
    Explanations

    -control

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     missing
    -0.07
     chubby
    -0.06
     mapped
    -0.06
     Arch
    -0.06
    subclass
    -0.06
     recommended
    -0.06
     notebooks
    -0.06
     talking
    -0.06
     interchangeable
    -0.06
     geared
    -0.06
    POSITIVE LOGITS
    BOT
    0.08
    之城
    0.07
    粹
    0.07
    Locator
    0.07
     blossom
    0.07
    燏
    0.07
     Ogre
    0.07
    嘁
    0.07
    сот
    0.07
    _features
    0.07
    Act Density 0.000%

    No Known Activations