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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Fi
    -0.07
    邮箱
    -0.07
    竞技
    -0.07
     Paint
    -0.07
    ☐
    -0.07
     Cord
    -0.06
    競
    -0.06
     doctoral
    -0.06
    ותר
    -0.06
     Gill
    -0.06
    POSITIVE LOGITS
     развитие
    0.07
    .arm
    0.07
    ibilidad
    0.07
    יבו
    0.07
    本身就是
    0.07
    Deposit
    0.07
    にく
    0.07
     มกร
    0.07
    .beans
    0.07
     часть
    0.07
    Act Density 0.008%

    No Known Activations