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

    Neuronpedia

    INDEX
    Explanations

    }}

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    香
    -0.07
    experience
    -0.07
    妹子
    -0.07
    mon
    -0.07
     starring
    -0.07
     few
    -0.07
    sing
    -0.07
     الكتاب
    -0.07
     welcomed
    -0.07
     Words
    -0.07
    POSITIVE LOGITS
    Ajax
    0.07
    魍
    0.07
    Collision
    0.07
    ציה
    0.07
    باء
    0.07
     {}\
    0.07
     uphe
    0.07
    מאי
    0.07
     mpz
    0.07
    (fullfile
    0.06
    Act Density 0.009%

    No Known Activations