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

    Neuronpedia

    INDEX
    Explanations

    more lively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тения
    0.75
     أل
    0.74
    ഹമ്മ
    0.70
     déc
    0.70
    类别
    0.70
    thin
    0.69
     অধীনে
    0.69
    binom
    0.69
    联赛
    0.69
    ี้ยง
    0.68
    POSITIVE LOGITS
     Sunset
    0.82
     Sunrise
    0.81
     checking
    0.73
     Sol
    0.72
     Murphy
    0.71
     clearing
    0.70
     Midnight
    0.70
     Checking
    0.70
     Short
    0.67
     Acceleration
    0.67
    Act Density 0.001%

    No Known Activations