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

    Neuronpedia

    INDEX
    Explanations

    structured data formats and programming constructs

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

    code snippets with version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.85
    ⓧ
    -0.56
     "..\..\..\
    -0.52
    المشاركات
    -0.49
    MLLoader
    -0.48
     ویکی‌پدی
    -0.48
     CommonModule
    -0.47
    RegressionTest
    -0.46
    });*/
    -0.46
    盎
    -0.46
    POSITIVE LOGITS
    endphp
    0.65
    hyung
    0.60
    IMAS
    0.56
    发表于
    0.52
    IZABETH
    0.51
    aini
    0.51
    googleapis
    0.50
    ần
    0.50
    Pautan
    0.49
    LogManager
    0.47
    Act Density 0.002%

    No Known Activations