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

    Neuronpedia

    INDEX
    Explanations

    stating what is needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    heva
    0.41
    đa
    0.40
    þ
    0.39
     Elena
    0.38
     Immunology
    0.38
    緘
    0.38
     académica
    0.37
     Engaging
    0.37
     Thursdays
    0.36
     Елена
    0.36
    POSITIVE LOGITS
     products
    0.46
     candle
    0.44
     facts
    0.44
     представляют
    0.43
    有哪些
    0.43
     bool
    0.42
     uptime
    0.41
     ఉంటాయి
    0.41
     candles
    0.41
     चुनें
    0.41
    Act Density 0.004%

    No Known Activations