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

    Neuronpedia

    INDEX
    Explanations

    class definitions and UI component identifiers in code

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

    UI components creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abestanden
    -0.57
    └──
    -0.49
    Datuak
    -0.49
    OGND
    -0.48
    arXiv
    -0.47
    ことの
    -0.46
    脚注の使い方
    -0.45
    TRIBUN
    -0.43
     mengal
    -0.43
     הבי
    -0.42
    POSITIVE LOGITS
    CloseOperation
    0.44
    findOrFail
    0.41
     GenerationType
    0.39
     ControllerBase
    0.38
    expandindo
    0.37
    PyExc
    0.36
    SuspendLayout
    0.36
    InternalFrame
    0.34
     JFrame
    0.34
    ChildScrollView
    0.34
    Act Density 0.002%

    No Known Activations