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

    Neuronpedia

    INDEX
    Explanations

    weather forecasting and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Holy
    0.48
     යු
    0.44
    Holy
    0.41
     Donkey
    0.40
     urine
    0.39
     holy
    0.38
    からない
    0.38
    יש
    0.38
     Polar
    0.38
     אור
    0.38
    POSITIVE LOGITS
     vane
    0.56
    proofing
    0.51
     vanes
    0.50
     getWeather
    0.47
     fenô
    0.47
    station
    0.46
    foil
    0.45
     phénomènes
    0.45
    霁
    0.44
    ेंस
    0.44
    Act Density 0.010%

    No Known Activations