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

    Neuronpedia

    INDEX
    Explanations

    purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zi
    0.72
     borough
    0.71
    __(
    0.71
    鐧
    0.70
     Positions
    0.68
    좀
    0.68
    نن
    0.67
    貳
    0.66
    相對
    0.66
     तित
    0.66
    POSITIVE LOGITS
     जैसे
    0.66
     inland
    0.62
     الكربون
    0.62
     Orders
    0.61
    캄
    0.61
     построил
    0.60
    assa
    0.59
    ্টের
    0.59
    order
    0.58
    apest
    0.57
    Act Density 0.018%

    No Known Activations