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

    Neuronpedia

    INDEX
    Explanations

    -target

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    怎么看
    -0.07
    .assert
    -0.07
    乐视
    -0.07
    奇
    -0.07
    没能
    -0.07
    ane
    -0.07
    ∀
    -0.07
     assess
    -0.07
    .isUser
    -0.07
    边际
    -0.07
    POSITIVE LOGITS
     quotas
    0.07
    ведения
    0.07
    حضار
    0.07
     하는
    0.07
    larından
    0.07
     restrictions
    0.07
    ağlı
    0.07
     وضع
    0.06
    鸨
    0.06
    텣
    0.06
    Act Density 0.000%

    No Known Activations