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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace characters or indentation in code

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

    method or code block ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndroidJUnit
    -0.50
    BufferException
    -0.44
    sizeCache
    -0.42
    verwijspagina
    -0.38
    :✨
    -0.36
    BigNumber
    -0.36
    typeDefinition
    -0.33
    èdent
    -0.33
     gynnwys
    -0.33
    fVar
    -0.33
    POSITIVE LOGITS
     NSCoder
    0.51
    UseVisualStyle
    0.48
     ToString
    0.48
    دانشنامهٔ
    0.47
    |()
    0.46
    AFFIRMED
    0.44
    Atsauces
    0.42
    tagHelperRunner
    0.42
    MemoryWarning
    0.42
     surla
    0.41
    Act Density 0.001%

    No Known Activations