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

    Neuronpedia

    INDEX
    Explanations

    mathematical intervals and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     odu
    0.50
    🎗
    0.45
    加班
    0.44
    ranges
    0.44
     ranges
    0.44
     celebrates
    0.43
     সংখ্যালঘু
    0.43
    鉾
    0.42
     배치
    0.41
     파인더
    0.41
    POSITIVE LOGITS
     $[-
    1.09
     [-
    1.06
     $[
    0.96
    [-
    0.93
    =[-
    0.90
     interval
    0.87
    $[
    0.84
     [
    0.82
    Interval
    0.79
    [-\
    0.75
    Act Density 0.016%

    No Known Activations