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

    Neuronpedia

    INDEX
    Explanations

    references to methods and variables related to data structures, particularly involving categories and prompts in code

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

    Code, names, and strings

    np_acts-logits-general · gemini-2.0-flash

    variable names, strings, or code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.47
    popper
    -0.47
    FetchType
    -0.45
     "'");
    -0.45
    CategoryId
    -0.44
     klant
    -0.43
     combatt
    -0.43
    cmath
    -0.42
    كونات
    -0.40
     hasattr
    -0.39
    POSITIVE LOGITS
    fromUtf
    0.82
    Tembelea
    0.78
    ConverterFactory
    0.78
    Personendaten
    0.72
    qrstuvwxyz
    0.71
    DockStyle
    0.68
    LookAnd
    0.67
    ]")]
    0.67
     string
    0.64
     AttributeSet
    0.63
    Act Density 0.328%

    No Known Activations