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

    Neuronpedia

    INDEX
    Explanations

    di

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expect
    -0.08
    綠
    -0.07
    (contents
    -0.07
    基金管理
    -0.07
    ᅦ
    -0.07
    腽
    -0.06
    |.
    -0.06
    겈
    -0.06
    ตำบ
    -0.06
     almost
    -0.06
    POSITIVE LOGITS
    imeter
    0.07
    하신
    0.07
    شور
    0.07
    כם
    0.07
    imei
    0.07
    terior
    0.07
    InternalServerError
    0.07
    iqué
    0.07
    찡
    0.07
    ё
    0.06
    Act Density 0.004%

    No Known Activations