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

    Neuronpedia

    INDEX
    Explanations

    temporal indicators and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amanho
    0.74
     multiplicative
    0.74
     अड्
    0.72
    चलिए
    0.72
    အောင်
    0.71
    अब
    0.71
     넘어
    0.70
    辈子
    0.70
    tikz
    0.69
     전부
    0.68
    POSITIVE LOGITS
     shortly
    3.37
     soon
    2.86
     Shortly
    2.76
    Shortly
    2.65
     вскоре
    2.26
     Soon
    2.18
    soon
    2.12
    Soon
    2.09
     moments
    2.03
     just
    2.03
    Act Density 0.122%

    No Known Activations