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

    Neuronpedia

    INDEX
    Explanations

    Okay, here are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hacking
    0.67
     ห
    0.66
    ຫ
    0.64
    iaz
    0.64
     लेवल
    0.63
    ha
    0.63
     lệnh
    0.62
     l
    0.61
    getApplication
    0.61
     ফাঁস
    0.61
    POSITIVE LOGITS
    wch
    0.64
    клон
    0.62
     مارس
    0.60
     प्री
    0.57
    mojo
    0.56
    вій
    0.56
     உள்ளிட்ட
    0.56
    োজন
    0.55
    वक
    0.55
    vol
    0.54
    Act Density 0.107%

    No Known Activations