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

    Neuronpedia

    INDEX
    Explanations

    sameness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piracy
    -0.07
    printw
    -0.07
     Gö
    -0.07
    weeks
    -0.07
     marketed
    -0.07
     wag
    -0.07
    (numpy
    -0.07
     salaries
    -0.06
     ไป
    -0.06
    lantı
    -0.06
    POSITIVE LOGITS
     ㅇㅇ
    0.06
     coefficients
    0.06
     bols
    0.06
     कब
    0.05
     KERNEL
    0.05
    ][_
    0.05
    插
    0.05
    ريم
    0.05
    所有
    0.05
     числа
    0.05
    Act Density 0.013%

    No Known Activations