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

    Neuronpedia

    INDEX
    Explanations

    the last periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जल्द
    0.89
     nantinya
    0.88
    훗
    0.88
     kasnije
    0.84
     ďal
    0.82
     விரைவில்
    0.82
     후에
    0.79
     впоследствии
    0.79
    Subsequently
    0.79
    කින්
    0.79
    POSITIVE LOGITS
     past
    3.97
    past
    3.24
     last
    3.22
    Past
    3.18
     Past
    3.12
     PAST
    2.85
    last
    2.83
    過去
    2.81
     afgelopen
    2.62
    Last
    2.58
    Act Density 0.088%

    No Known Activations