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

    Neuronpedia

    INDEX
    Explanations

    declining or slowing trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    离子
    0.49
    饮食
    0.48
     kullanıcı
    0.46
    协助
    0.46
    聪
    0.46
    让
    0.44
    对象
    0.43
     segítség
    0.43
    ısı
    0.42
     ઉપયોગ
    0.42
    POSITIVE LOGITS
     lows
    0.61
    year
    0.55
     years
    0.55
     decline
    0.54
     trend
    0.54
    years
    0.53
     peak
    0.52
     year
    0.50
    peak
    0.49
     YoY
    0.49
    Act Density 0.118%

    No Known Activations