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

    Neuronpedia

    INDEX
    Explanations

    the primary focus or important aspects of various topics or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    main followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.86
    ﹧
    -0.78
     незавершена
    -0.77
     témoig
    -0.74
     autorytatywna
    -0.73
    RenderAtEndOf
    -0.73
    TemporalType
    -0.72
    Personendaten
    -0.72
     propOrder
    -0.72
    <unused41>
    -0.71
    POSITIVE LOGITS
     main
    1.18
    main
    0.94
    Main
    0.92
     MAIN
    0.88
     Main
    0.87
    MAIN
    0.83
     Haupt
    0.79
     głów
    0.74
     principaux
    0.73
     hlavní
    0.72
    Act Density 0.018%

    No Known Activations