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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الماضي
    -0.08
    憧憬
    -0.08
     использов
    -0.08
    合わ
    -0.07
    贡献力量
    -0.07
    getPath
    -0.07
     Ava
    -0.07
     çalıştı
    -0.07
    わか
    -0.07
    取胜
    -0.07
    POSITIVE LOGITS
    )",
    0.07
    )".
    0.07
    ?',
    0.07
    !',
    0.07
     mean
    0.06
    ')[
    0.06
    "]],↵
    0.06
    )");↵
    0.06
    Program
    0.06
     potions
    0.06
    Act Density 0.054%

    No Known Activations