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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    对公司
    -0.08
    john
    -0.07
     Leigh
    -0.07
     porno
    -0.07
    _chan
    -0.07
    sel
    -0.07
    这个地图
    -0.07
    coal
    -0.07
    _fm
    -0.06
    >'
    -0.06
    POSITIVE LOGITS
     task
    0.08
     وجود
    0.07
    行走
    0.07
    骁
    0.07
     increased
    0.07
    _access
    0.07
    "],"
    0.07
    天地
    0.06
    اف
    0.06
     per
    0.06
    Act Density 0.043%

    No Known Activations