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

    Neuronpedia

    INDEX
    Explanations

    build for production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     स्थापना
    0.42
    DataAnnotations
    0.42
     Blot
    0.41
    DebugTest
    0.40
    试验
    0.39
    द्रोह
    0.38
    Prog
    0.38
     імен
    0.38
    Macros
    0.38
     Bacteriol
    0.37
    POSITIVE LOGITS
    build
    0.88
     build
    0.87
     Build
    0.76
     builds
    0.73
    Build
    0.71
    打包
    0.69
    BUILD
    0.63
    ビル
    0.63
     Builds
    0.62
     production
    0.60
    Act Density 0.009%

    No Known Activations