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

    Neuronpedia

    INDEX
    Explanations

    representations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,D
    -0.07
     Ye
    -0.07
    输送
    -0.07
    ng
    -0.07
    ふ
    -0.07
     Ihnen
    -0.06
    _THE
    -0.06
    -develop
    -0.06
     Sample
    -0.06
    惠民
    -0.06
    POSITIVE LOGITS
    ario
    0.07
    hours
    0.07
    ייצג
    0.07
    윅
    0.07
    壁
    0.07
    (lr
    0.07
    פו
    0.07
    ומו
    0.06
    .cum
    0.06
     panic
    0.06
    Act Density 0.005%

    No Known Activations