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

    Neuronpedia

    INDEX
    Explanations

    Technical/Mathematical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bol
    -0.06
     kernel
    -0.06
     attacked
    -0.06
    _gener
    -0.06
     ux
    -0.06
    .name
    -0.06
     devices
    -0.06
    ‐
    -0.06
    ，而
    -0.06
    _transition
    -0.06
    POSITIVE LOGITS
     нельзя
    0.07
    廠
    0.07
     mã
    0.06
     день
    0.06
     finder
    0.06
    maids
    0.06
    特色
    0.06
    :expr
    0.06
     sơn
    0.06
     galer
    0.06
    Act Density 0.204%

    No Known Activations