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

    Neuronpedia

    INDEX
    Explanations

    C++ iostream includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ైన
    0.61
     seura
    0.60
     modalités
    0.60
     रिलेशन
    0.59
     tillage
    0.58
     ヨコハマ
    0.58
     MTV
    0.57
     চর
    0.56
     rites
    0.56
    MTV
    0.56
    POSITIVE LOGITS
     Bars
    0.70
     pH
    0.67
    pH
    0.66
    chromed
    0.65
     시장
    0.65
    BBB
    0.64
    Speed
    0.63
    Bar
    0.62
    市場
    0.61
     anda
    0.61
    Act Density 0.039%

    No Known Activations