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

    Neuronpedia

    INDEX
    Explanations

    specific dates and months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     July
    1.27
     october
    1.25
     June
    1.25
    July
    1.24
    June
    1.24
    October
    1.24
     October
    1.24
    September
    1.23
     September
    1.23
    April
    1.15
    POSITIVE LOGITS
    ราช
    0.79
     손
    0.74
    ذلك
    0.74
    fillText
    0.74
     Çok
    0.72
    Kalau
    0.72
    脓
    0.71
     veramente
    0.70
     सीरियल
    0.70
     cadast
    0.70
    Act Density 0.058%

    No Known Activations