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

    Neuronpedia

    INDEX
    Explanations

    explaining meanings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    珢
    0.41
    马
    0.40
    尝试
    0.39
    Overview
    0.39
    调
    0.39
    保护
    0.38
    Protection
    0.38
    ␥
    0.38
     Sequencing
    0.38
    ستر
    0.37
    POSITIVE LOGITS
    这句话
    0.59
     هذا
    0.57
     meaning
    0.55
    意味
    0.54
    meaning
    0.54
    这话
    0.54
     의미
    0.52
     worded
    0.51
     означает
    0.50
     означа
    0.48
    Act Density 0.088%

    No Known Activations