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

    Neuronpedia

    INDEX
    Explanations

    health or treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etc
    0.62
     हेतु
    0.61
     Troy
    0.58
     cool
    0.57
     succession
    0.57
     ali
    0.57
     ri
    0.56
     Tab
    0.56
     Etc
    0.56
     они
    0.55
    POSITIVE LOGITS
    çuk
    0.86
    לק
    0.77
     原子
    0.76
     તમારી
    0.76
     organisations
    0.75
     தாக்கு
    0.75
    ucionales
    0.74
    adig
    0.73
     organizations
    0.73
     বিনষ্ট
    0.72
    Act Density 0.003%

    No Known Activations