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

    Neuronpedia

    INDEX
    Explanations

    references to privacy keywords in programming contexts

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

    private and fileprivate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    osexuality
    -0.49
    extAlignment
    -0.48
    chtigkeit
    -0.46
    ofire
    -0.46
    ariConfig
    -0.43
    EndGlobal
    -0.42
    isexual
    -0.42
     uVar
    -0.41
     hochzeit
    -0.41
     calda
    -0.41
    POSITIVE LOGITS
    private
    2.41
     private
    2.17
    Private
    1.93
     Private
    1.86
     PRIVATE
    1.75
    PRIVATE
    1.59
     privaten
    1.47
     privado
    1.45
     privada
    1.43
     privately
    1.42
    Act Density 0.002%

    No Known Activations