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

    Neuronpedia

    INDEX
    Explanations

    attempt or awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beliau
    0.66
     сами
    0.61
     তাঁদের
    0.61
     sami
    0.60
     చేస్తున్నారు
    0.60
    하시
    0.59
     তাঁরা
    0.58
     তিনি
    0.57
    他们的
    0.57
     చేశారు
    0.56
    POSITIVE LOGITS
     itself
    1.37
     its
    0.91
    本身
    0.79
     Its
    0.75
    Its
    0.74
    its
    0.67
     ತನ್ನ
    0.65
     자체
    0.64
     aldığı
    0.64
    自体
    0.63
    Act Density 0.016%

    No Known Activations