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

    Neuronpedia

    INDEX
    Explanations

    use instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    selves
    1.53
    ters
    1.37
    ed
    1.34
     introns
    1.33
    要是
    1.29
    shares
    1.28
    एको
    1.27
    新生
    1.25
    为何
    1.24
    を買
    1.23
    POSITIVE LOGITS
    ர்
    1.68
     движение
    1.68
    क
    1.65
    ية
    1.54
    ب
    1.53
    ко
    1.52
    크
    1.43
     шаг
    1.39
    ่า
    1.38
    פר
    1.38
    Act Density 0.154%

    No Known Activations