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

    Neuronpedia

    INDEX
    Explanations

    instances of the keyword "private" and modifiers related to class visibility in code

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

    `private` and `static` keywords

    np_acts-logits-general · gemini-2.0-flash

    private followed by type or modifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poppies
    -0.70
     فريبيس
    -0.69
     pstmt
    -0.65
    waitKey
    -0.62
    XmlSchema
    -0.61
     Uff
    -0.60
     wafers
    -0.60
    ostante
    -0.60
     Poppy
    -0.60
     nawr
    -0.59
    POSITIVE LOGITS
    帖最后由
    0.77
     readonly
    0.74
     static
    0.74
     Saltar
    0.73
    økt
    0.71
     Steele
    0.69
     Steine
    0.68
    eria
    0.65
    rawDesc
    0.65
     Bate
    0.64
    Act Density 0.017%

    No Known Activations