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

    Neuronpedia

    INDEX
    Explanations

    data sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vicious
    -0.07
     Vin
    -0.07
    يع
    -0.06
     Bread
    -0.06
    عة
    -0.06
    樹
    -0.06
    -btn
    -0.06
     Solomon
    -0.06
     Pa
    -0.06
    Vin
    -0.06
    POSITIVE LOGITS
    :SetPoint
    0.07
    ERENCE
    0.07
    ประม
    0.07
     نیرو
    0.07
    screen
    0.07
    ทาง
    0.07
    (FLAGS
    0.06
     ikt
    0.06
    (exec
    0.06
    camera
    0.06
    Act Density 0.049%

    No Known Activations