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

    Neuronpedia

    INDEX
    Explanations

    increase in occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evolved
    0.48
     repeatedly
    0.46
     evolving
    0.44
     недостаточно
    0.39
    urr
    0.38
     continually
    0.38
     ткани
    0.38
    Countdown
    0.37
     সমূহ
    0.37
    Ongoing
    0.37
    POSITIVE LOGITS
     births
    0.83
     marriages
    0.83
     arrests
    0.80
     instances
    0.79
     incidences
    0.72
     occurrences
    0.71
    instances
    0.71
     cases
    0.71
     случаев
    0.70
     requests
    0.69
    Act Density 0.012%

    No Known Activations