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

    Neuronpedia

    INDEX
    Explanations

    references to a base class or structure in programming

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

    Base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.68
     فريبيس
    -0.65
     estekak
    -0.63
     CreateTagHelper
    -0.61
    AddHtmlAttribute
    -0.58
     ویکی‌پدی
    -0.57
    !*\
    -0.57
     nahilalakip
    -0.56
    ьаж
    -0.55
    extAlignment
    -0.54
    POSITIVE LOGITS
    Base
    2.34
     Base
    1.70
    BASE
    1.40
    base
    1.26
     BASE
    1.21
     base
    1.10
    IBase
    1.05
    BaseModel
    1.04
    Bases
    0.94
    BaseResponse
    0.92
    Act Density 0.006%

    No Known Activations