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

    Neuronpedia

    INDEX
    Explanations

    first round playoff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dive
    0.43
    igan
    0.39
     mistake
    0.39
     Dive
    0.38
     sprzedaży
    0.37
     फाइनल
    0.36
    aginaw
    0.36
    dives
    0.36
     sucesivamente
    0.36
     менее
    0.35
    POSITIVE LOGITS
     निर्धारित
    0.41
    ट्टर
    0.40
    rantes
    0.38
     outburst
    0.37
     outbursts
    0.37
    谈判
    0.37
    哄
    0.37
     Mar
    0.37
     তাহাদের
    0.37
     독
    0.37
    Act Density 0.006%

    No Known Activations