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

    Neuronpedia

    INDEX
    Explanations

    use math formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iação
    0.39
    roph
    0.39
     Rabu
    0.39
     Mittwoch
    0.39
    guien
    0.38
    ینی
    0.38
     tallest
    0.38
    punkt
    0.37
     Sunlight
    0.37
    ramient
    0.37
    POSITIVE LOGITS
     formula
    0.47
     formul
    0.44
     forecasting
    0.43
     fórmula
    0.43
     futur
    0.42
     exponential
    0.41
     looping
    0.41
    ::
    0.41
     公式
    0.41
     прогнозы
    0.41
    Act Density 0.001%

    No Known Activations