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

    Neuronpedia

    INDEX
    Explanations

    .module

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    刷
    -0.07
     independence
    -0.06
     Carlo
    -0.06
    ère
    -0.06
     gust
    -0.06
    rne
    -0.06
    ，说
    -0.06
    Average
    -0.06
    žen
    -0.06
     OBS
    -0.06
    POSITIVE LOGITS
    .module
    0.10
    module
    0.08
    osition
    0.07
    ';↵
    0.06
    ρων
    0.06
    ]")
    0.06
    Зап
    0.06
     Outputs
    0.06
    ilmesi
    0.06
     تأ
    0.06
    Act Density 0.000%

    No Known Activations