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

    Neuronpedia

    INDEX
    Explanations

    worked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ساز
    -0.07
    -May
    -0.07
    ┴
    -0.06
     Github
    -0.06
    ,msg
    -0.06
     آیا
    -0.06
     詳細
    -0.06
     roadmap
    -0.06
     риз
    -0.06
    ений
    -0.06
    POSITIVE LOGITS
    870
    0.07
    kerja
    0.07
     worked
    0.07
     обязан
    0.07
     working
    0.07
     Working
    0.07
     Seal
    0.06
     cria
    0.06
     executives
    0.06
    cor
    0.06
    Act Density 0.024%

    No Known Activations