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

    Neuronpedia

    INDEX
    Explanations

    references to constants in programming or mathematical contexts

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

    const keyword and punctuation or variable types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.61
    WebServlet
    -0.59
    QMetaType
    -0.57
     getID
    -0.57
    存于互联网档案馆
    -0.57
     Gelen
    -0.56
    getID
    -0.56
     насељу
    -0.56
    Paging
    -0.56
    bootstrapcdn
    -0.55
    POSITIVE LOGITS
    const
    1.06
     const
    0.94
    Const
    0.92
     Const
    0.92
     Constable
    0.74
    CONST
    0.71
     CONST
    0.67
    consts
    0.64
    Consts
    0.62
    Constantes
    0.60
    Act Density 0.004%

    No Known Activations