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

    Neuronpedia

    INDEX
    Explanations

    starting/running code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taylor
    0.47
     Intellectual
    0.44
     intellectual
    0.43
     TAYLOR
    0.43
     taglio
    0.40
     Boxer
    0.39
     Bass
    0.38
     sparring
    0.38
     बेड
    0.38
     Mow
    0.37
    POSITIVE LOGITS
    mainloop
    1.08
    启动
    1.03
    起動
    1.03
     runApp
    0.96
    运行
    0.93
    run
    0.90
     run
    0.88
     uruch
    0.88
    Run
    0.88
    main
    0.87
    Act Density 0.044%

    No Known Activations