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

    Neuronpedia

    INDEX
    Explanations

    data structure and programming-related concepts

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

    code and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.56
     Jefus
    -0.53
     Theſe
    -0.48
     itſelf
    -0.47
     Reſ
    -0.47
     Monfieur
    -0.47
     Utama
    -0.47
     Geſ
    -0.46
    ſelf
    -0.46
     Majefty
    -0.44
    POSITIVE LOGITS
     NSCoder
    0.76
    abstractmethod
    0.73
    Hentet
    0.59
    ьаж
    0.58
    Obrázky
    0.57
    хьтан
    0.56
     ContentValues
    0.54
    LLocation
    0.54
    Personensuche
    0.54
    Diwedd
    0.54
    Act Density 0.024%

    No Known Activations