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

    Neuronpedia

    INDEX
    Explanations

    abstract thought and reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     directorio
    0.42
     diversité
    0.42
     AppBsky
    0.41
     razvoj
    0.41
     énfasis
    0.41
    ibilités
    0.39
     almac
    0.39
     noção
    0.39
     উদ্ভি
    0.38
     recort
    0.38
    POSITIVE LOGITS
     quantitative
    0.77
     quantitatively
    0.77
    Quantitative
    0.77
     Quantitative
    0.73
    quantitative
    0.72
    quant
    0.69
    Quant
    0.63
     Quant
    0.60
     quant
    0.59
    定量
    0.55
    Act Density 0.001%

    No Known Activations