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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Exit
    -0.08
    自然保护
    -0.07
     товаров
    -0.07
     Algorithms
    -0.07
    _coeff
    -0.07
     Hospital
    -0.07
    控股股东
    -0.07
    ידע
    -0.07
     информ
    -0.07
    מיכה
    -0.07
    POSITIVE LOGITS
    ��
    0.08
    .mixer
    0.08
     broken
    0.07
    尖
    0.07
     disposing
    0.07
    ڭ
    0.07
    chie
    0.06
     brushes
    0.06
    预定
    0.06
    (car
    0.06
    Act Density 0.029%

    No Known Activations