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

    Neuronpedia

    INDEX
    Explanations

    instances of nested parentheses in code

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

    start of turn or code block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebServlet
    -0.54
    ScopeManager
    -0.49
    ViewFeatures
    -0.49
     nonUne
    -0.49
    Personensuche
    -0.49
    jspx
    -0.47
    mybatisplus
    -0.47
    الحياه
    -0.47
    もしれません
    -0.47
    UnknownFieldSet
    -0.46
    POSITIVE LOGITS
    ((
    1.41
     ((
    1.22
    (((
    1.02
    >((
    0.96
     (((
    0.96
    ((((
    0.89
    )((
    0.87
    =((
    0.83
    [(
    0.82
     [(
    0.81
    Act Density 0.001%

    No Known Activations