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

    Neuronpedia

    INDEX
    Explanations

    news from governments and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    计算
    0.47
    记忆
    0.46
    Coefficient
    0.45
     时
    0.45
    品质
    0.45
     값을
    0.45
    产生
    0.44
     значение
    0.44
    节省
    0.44
    经典的
    0.44
    POSITIVE LOGITS
     reportedly
    0.68
    umumkan
    0.65
     announced
    0.64
     Reuters
    0.63
    Reuters
    0.61
     anunció
    0.61
     Biden
    0.60
     tweeted
    0.58
     शुक्रवार
    0.57
     বুধবার
    0.57
    Act Density 0.119%

    No Known Activations