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

    Neuronpedia

    INDEX
    Explanations

    Percentage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foo
    -0.08
    ulti
    -0.07
    ップ
    -0.06
    getConnection
    -0.06
     se
    -0.06
     وال
    -0.06
     venues
    -0.06
    createFrom
    -0.06
    ielding
    -0.06
    او
    -0.06
    POSITIVE LOGITS
     Dh
    0.08
     Please
    0.07
     ill
    0.06
    　 　 　 　
    0.06
     ژوئ
    0.06
     ​​​
    0.06
    _tF
    0.06
    bh
    0.06
    ги
    0.06
    ...(
    0.06
    Act Density 0.001%

    No Known Activations