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

    Neuronpedia

    INDEX
    Explanations

    visible page content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fourteen
    0.43
     penurunan
    0.39
    Lonely
    0.38
    ര്‍ക്കും
    0.37
     ১৪
    0.37
     Fifteen
    0.36
     १५
    0.35
    િયલ
    0.35
    が良い
    0.34
     गहरी
    0.34
    POSITIVE LOGITS
    3
    0.57
    三
    0.44
    ۳
    0.42
    <0xBB>
    0.38
     ۳
    0.38
    three
    0.37
     国内
    0.37
     three
    0.37
     THREE
    0.36
    三天
    0.35
    Act Density 0.004%

    No Known Activations