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

    Neuronpedia

    INDEX
    Explanations

    Svelte code components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plage
    0.43
    ᅥ
    0.43
     indign
    0.43
    бору
    0.43
     Recht
    0.42
     ні
    0.42
     вмеша
    0.41
     കാരണ
    0.41
     जोन
    0.41
     idolat
    0.41
    POSITIVE LOGITS
    require
    0.48
    代码
    0.47
     mainline
    0.47
    main
    0.46
     development
    0.45
    Main
    0.45
     main
    0.43
    Runnable
    0.43
    Compile
    0.43
    umd
    0.43
    Act Density 0.069%

    No Known Activations