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

    Neuronpedia

    INDEX
    Explanations

    weekly reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     REGIUNI
    0.77
     GOT
    0.75
    را
    0.71
     মৃতের
    0.71
     carousel
    0.71
    Он
    0.71
    Gọi
    0.71
     phoned
    0.70
     candle
    0.69
     called
    0.68
    POSITIVE LOGITS
    act
    0.86
    ą
    0.86
    buildings
    0.85
    urile
    0.80
    weekly
    0.79
    adas
    0.79
    wel
    0.78
    ighth
    0.78
     इंट्रा
    0.78
    bel
    0.77
    Act Density 0.003%

    No Known Activations