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

    Neuronpedia

    INDEX
    Explanations

    JavaScript variable declarations and associated functions

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

    javascript code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.52
    awtextra
    -0.49
     continúas
    -0.46
    LayoutStyle
    -0.45
    CppCodeGen
    -0.45
     ब्रेकडाउन
    -0.45
     propOrder
    -0.42
     surla
    -0.41
     <",
    -0.40
     désolés
    -0.40
    POSITIVE LOGITS
     Taktlose
    0.48
    
    0.46
    Viitteet
    0.45
    IsMutable
    0.45
    postIndex
    0.41
    WaitGroup
    0.41
     OMITBAD
    0.40
     createState
    0.39
    تقاوى
    0.39
    挥
    0.39
    Act Density 0.012%

    No Known Activations