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

    Neuronpedia

    INDEX
    Explanations

    diet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ne
    -0.07
     Báo
    -0.07
     Ky
    -0.07
     �
    -0.07
    电话
    -0.07
    ジュ
    -0.07
    مواقف
    -0.06
    ymoon
    -0.06
     التج
    -0.06
     XK
    -0.06
    POSITIVE LOGITS
    _math
    0.08
    ㉣
    0.07
    !="
    0.07
    libs
    0.07
     Galactic
    0.07
     Formatting
    0.07
    $string
    0.07
     yaşayan
    0.07
     내가
    0.06
    (Database
    0.06
    Act Density 0.013%

    No Known Activations