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

    Neuronpedia

    INDEX
    Explanations

    uh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     branch
    -0.07
     feels
    -0.07
    炒
    -0.07
    Prot
    -0.07
     git
    -0.07
     ürün
    -0.07
    >User
    -0.06
    百分
    -0.06
     Kenn
    -0.06
     ".");↵
    -0.06
    POSITIVE LOGITS
     troublesome
    0.07
    吃惊
    0.07
     Truck
    0.07
    넴
    0.07
     이야
    0.07
    来了
    0.07
    림
    0.07
    _RAM
    0.07
     miser
    0.07
     rematch
    0.07
    Act Density 0.002%

    No Known Activations