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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scrutiny
    -0.07
    挣扎
    -0.07
    -oper
    -0.07
    _traffic
    -0.07
    -design
    -0.06
    inders
    -0.06
     reducing
    -0.06
    itizer
    -0.06
    Arrange
    -0.06
    上市公司
    -0.06
    POSITIVE LOGITS
    _school
    0.07
    不仅能
    0.07
     الوح
    0.07
     الجديدة
    0.07
    CORD
    0.07
     Cort
    0.07
     sina
    0.06
     günd
    0.06
     Maver
    0.06
     Apart
    0.06
    Act Density 0.004%

    No Known Activations