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

    Neuronpedia

    INDEX
    Explanations

    planning or tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pandemic
    0.45
     financial
    0.42
    Including
    0.42
    *
    0.42
    Your
    0.41
     worldwide
    0.40
    financial
    0.40
     clientele
    0.40
    ‌
    0.39
    ight
    0.39
    POSITIVE LOGITS
     некоторое
    0.50
     ඔහු
    0.46
    ógł
    0.44
     शायद
    0.44
     Bugün
    0.44
     übrigens
    0.44
     त्याने
    0.44
    ธิบาย
    0.43
    试图
    0.43
     neige
    0.43
    Act Density 0.004%

    No Known Activations