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

    Neuronpedia

    INDEX
    Explanations

    references to private and secure data handling

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

    private key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abestanden
    -0.83
     resourceCulture
    -0.82
     незавершена
    -0.80
    contentLoaded
    -0.79
    CloseOperation
    -0.73
    windowFixed
    -0.72
    хьтан
    -0.71
     disambiguazione
    -0.71
    ChildScrollView
    -0.69
     مشين
    -0.68
    POSITIVE LOGITS
     private
    0.52
    private
    0.48
     public
    0.45
    PRIVATE
    0.41
     Private
    0.39
     White
    0.38
    Private
    0.38
     Black
    0.38
     secret
    0.36
     PRIVATE
    0.36
    Act Density 0.076%

    No Known Activations