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

    Neuronpedia

    INDEX
    Explanations

    variety of, one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     organism
    0.41
     worms
    0.39
     deformed
    0.39
    Ultr
    0.39
     claws
    0.37
     (
    0.35
     PHY
    0.35
     contents
    0.35
     fusion
    0.35
     dielectric
    0.35
    POSITIVE LOGITS
     अमाउंट
    0.54
     그러면은
    0.49
    ডাক্ট
    0.48
     ahorita
    0.48
     बेसिकली
    0.47
     एक्सपेक्ट
    0.46
     परसेंटेज
    0.45
    🫣
    0.45
    сторінку
    0.45
     Ouais
    0.45
    Act Density 0.001%

    No Known Activations