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

    Neuronpedia

    INDEX
    Explanations

    structured sections and organizational elements in academic papers

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

    beginning of texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diwedd
    -0.85
     AssemblyCompany
    -0.78
    MigrationBuilder
    -0.74
    MLLoader
    -0.73
     Taktlose
    -0.73
    ViewImports
    -0.72
     الرياضيه
    -0.71
    XmlAccessType
    -0.69
    aarrggbb
    -0.69
    principalColumn
    -0.69
    POSITIVE LOGITS
     identification
    0.28
    assertArray
    0.27
     co
    0.25
     görün
    0.25
     появляется
    0.25
     assorted
    0.25
     various
    0.25
     poichè
    0.25
     chứng
    0.24
     визна
    0.24
    Act Density 0.023%

    No Known Activations