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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    实习生
    -0.08
    郏
    -0.07
     yuan
    -0.07
     API
    -0.07
    ICT
    -0.07
    证件
    -0.07
    �
    -0.07
     Florian
    -0.07
    mars
    -0.07
    _BB
    -0.07
    POSITIVE LOGITS
    ()`
    0.07
    "]
    0.07
     Capital
    0.07
     joined
    0.07
    square
    0.07
     '')
    0.07
    價值
    0.07
    descending
    0.07
    .cuda
    0.06
    ḥ
    0.06
    Act Density 0.170%

    No Known Activations