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

    Neuronpedia

    INDEX
    Explanations

    dates and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     преми
    0.45
    🎐
    0.41
    🥛
    0.41
     signUp
    0.39
    🍉
    0.39
     geliş
    0.38
    这时
    0.38
    कांक्षा
    0.38
     büy
    0.38
    খা
    0.38
    POSITIVE LOGITS
    since
    0.68
    截至
    0.66
     منذ
    0.62
     since
    0.60
    records
    0.56
     Since
    0.54
     cumulative
    0.54
     January
    0.52
    desde
    0.51
    過去
    0.51
    Act Density 0.041%

    No Known Activations