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

    Neuronpedia

    INDEX
    Explanations

    health and classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Istanbul
    0.44
    Undo
    0.41
     با
    0.41
     দ্বি
    0.41
    MyToolkit
    0.40
    Helvetica
    0.40
     衣装
    0.39
     lineWidth
    0.39
    0.39
     স্ক
    0.39
    POSITIVE LOGITS
     epidemi
    0.64
     și
    0.55
     chiropractor
    0.49
     orthopedic
    0.49
     restrooms
    0.49
     isn
    0.48
     septic
    0.48
     clinic
    0.47
     county
    0.47
     Veterin
    0.47
    Act Density 0.002%

    No Known Activations