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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jihad
    -0.07
    _js
    -0.07
    joint
    -0.07
    oriously
    -0.07
    חוו
    -0.07
    raf
    -0.06
    ジョン
    -0.06
    シンプル
    -0.06
    seudo
    -0.06
    \base
    -0.06
    POSITIVE LOGITS
    ());
↵
↵
    0.09
     noexcept
    0.07
     */
    0.07
     Detailed
    0.07
     שלה
    0.07
    	actual
    0.07
     để
    0.07
     enumer
    0.07
     ensured
    0.07
     месяц
    0.07
    Act Density 0.054%

    No Known Activations