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

    Neuronpedia

    INDEX
    Explanations

    name placeholder followed by closing bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roadmap
    1.67
     आईआईटी
    1.62
     आईआई
    1.61
     algorithmic
    1.55
     scalable
    1.55
     제도
    1.52
    ChatGPT
    1.49
    Basel
    1.45
     Roadmap
    1.45
     Лондон
    1.44
    POSITIVE LOGITS
     parishioners
    1.23
     camping
    1.01
     Masonic
    0.98
     ranchers
    0.97
     families
    0.96
     campers
    0.94
     campground
    0.94
     prese
    0.92
     religioso
    0.92
     Saginaw
    0.92
    Act Density 0.503%

    No Known Activations