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

    Neuronpedia

    INDEX
    Explanations

    time measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    制度
    -0.09
    _pres
    -0.09
    沿
    -0.09
    .symbol
    -0.08
     situações
    -0.08
     accountability
    -0.08
     행사
    -0.07
     quanh
    -0.07
     강조
    -0.07
     trin
    -0.07
    POSITIVE LOGITS
     CPU
    0.13
    CPU
    0.11
     slower
    0.11
     noticeably
    0.11
    elapsed
    0.11
     computational
    0.11
    speed
    0.11
    _cpu
    0.10
     elapsed
    0.10
     времени
    0.10
    Act Density 0.020%

    No Known Activations