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

    Neuronpedia

    INDEX
    Explanations

    references to code and programming constructs

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

    it under the terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.54
    +#+
    -0.54
    exitRule
    -0.52
    NameInMap
    -0.42
     المعيارى
    -0.41
    sizeCache
    -0.39
    BASEPATH
    -0.38
    sidemargin
    -0.38
     cumplido
    -0.38
     препратки
    -0.38
    POSITIVE LOGITS
    FunctionFlags
    0.56
     code
    0.52
     concrete
    0.51
     method
    0.50
     Meksiku
    0.50
     ModelExpression
    0.48
     contents
    0.47
    くちゃ
    0.44
     content
    0.43
    concrete
    0.43
    Act Density 0.001%

    No Known Activations