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

    Neuronpedia

    INDEX
    Explanations

    positive change and growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consistently
    0.44
     consistent
    0.43
    Consistent
    0.41
     sequential
    0.41
     ধারাবাহিক
    0.40
    oop
    0.39
     persistently
    0.39
    Sequential
    0.39
     successive
    0.39
     어려
    0.38
    POSITIVE LOGITS
     newfound
    1.52
     renewed
    1.27
     strengthened
    1.08
     deepened
    0.91
     changed
    0.91
     invigor
    0.90
     renew
    0.89
    renew
    0.88
     enriched
    0.88
     gained
    0.84
    Act Density 0.011%

    No Known Activations