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

    Neuronpedia

    INDEX
    Explanations

    npm run script names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Babe
    0.47
     Messiah
    0.41
     McMillan
    0.40
     junction
    0.39
     DIVISION
    0.39
     Division
    0.38
     perintah
    0.38
     실행
    0.37
     executing
    0.37
     commanded
    0.37
    POSITIVE LOGITS
    deploy
    0.54
    build
    0.50
    lint
    0.48
    test
    0.45
     publish
    0.45
     deploy
    0.45
    debug
    0.44
    Test
    0.44
     build
    0.43
    simulate
    0.43
    Act Density 0.002%

    No Known Activations