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

    Neuronpedia

    INDEX
    Explanations

    run configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Uly
    0.43
    freetype
    0.40
    Intu
    0.40
     сай
    0.39
    anzitutto
    0.38
    Detective
    0.38
    源代码
    0.38
    钳
    0.38
    侵
    0.38
     مشاهده
    0.37
    POSITIVE LOGITS
     runners
    0.70
     runner
    0.66
     Runners
    0.66
    runners
    0.64
     configurations
    0.61
     Run
    0.59
     Runner
    0.58
     run
    0.58
    Run
    0.57
     RUN
    0.55
    Act Density 0.003%

    No Known Activations