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

    Neuronpedia

    INDEX
    Explanations

    references to empty strings or lines in code and related discussions

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

    empty lines or strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.38
     commutative
    -0.32
     QtWidgets
    -0.32
    conserv
    -0.29
     Glob
    -0.29
    classmethod
    -0.29
     Vener
    -0.29
     عج
    -0.29
    merry
    -0.29
     TextAppearance
    -0.28
    POSITIVE LOGITS
    ValueStyle
    0.78
    rungsseite
    0.66
     CanadaChoose
    0.65
     المعيارى
    0.59
    ⮕
    0.59
    Atsauces
    0.58
     empty
    0.58
    TypedDataSet
    0.57
     архивлан
    0.57
     GenerationType
    0.56
    Act Density 0.064%

    No Known Activations