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

    Neuronpedia

    INDEX
    Explanations

    references to dialog interface components in programming

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

    user input or code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.88
    verwijspagina
    -0.86
     Италијани
    -0.79
    <unused8>
    -0.75
    <unused41>
    -0.75
    [@BOS@]
    -0.75
    <unused43>
    -0.75
    <unused74>
    -0.75
    <unused14>
    -0.74
    <unused16>
    -0.74
    POSITIVE LOGITS
    WindowConstants
    1.13
    ValueStyle
    0.87
    OutputType
    0.78
    setDisplay
    0.69
    signOut
    0.65
    BeforeClass
    0.52
    AfterClass
    0.45
    fadeOut
    0.45
     sessionFactory
    0.40
    dataTables
    0.40
    Act Density 0.001%

    No Known Activations