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

    Neuronpedia

    INDEX
    Explanations

    small degree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yu
    -0.07
    _tc
    -0.07
    .land
    -0.07
    鲔
    -0.06
     OCD
    -0.06
    _child
    -0.06
    .getPrice
    -0.06
     mocking
    -0.06
     vocabulary
    -0.06
     Deb
    -0.06
    POSITIVE LOGITS
     flags
    0.08
    @login
    0.07
    racial
    0.07
    Об
    0.07
    批准
    0.07
    -private
    0.07
    M
    0.07
    Ass
    0.06
    留
    0.06
    后勤
    0.06
    Act Density 0.075%

    No Known Activations