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

    Neuronpedia

    INDEX
    Explanations

    current trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     routine
    0.41
    是我
    0.39
     principally
    0.38
     optimization
    0.38
     deployment
    0.38
     optimizations
    0.38
     equivalence
    0.38
     lubrication
    0.38
     stupe
    0.37
    ∃
    0.37
    POSITIVE LOGITS
     trends
    1.98
     Trends
    1.88
     trend
    1.84
     trending
    1.73
    トレンド
    1.66
     Trend
    1.63
    Trends
    1.63
    trends
    1.62
     trendy
    1.60
    趋势
    1.59
    Act Density 0.024%

    No Known Activations