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

    Neuronpedia

    INDEX
    Explanations

    median of lists and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嶋
    0.42
    syllabus
    0.39
    밍
    0.38
    模块
    0.38
    sar
    0.38
    adhat
    0.38
    tant
    0.37
    HOOK
    0.37
    芘
    0.37
    ósitos
    0.37
    POSITIVE LOGITS
     median
    0.52
     Median
    0.49
     price
    0.48
     Price
    0.46
    Median
    0.44
    Price
    0.43
     giá
    0.43
    값
    0.43
     lethal
    0.42
     elapsed
    0.42
    Act Density 0.005%

    No Known Activations