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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and structures, particularly focusing on templates and classes in a programming context

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

    C++ code, especially template/header related code

    np_acts-logits-general · gemini-2.0-flash

    code followed by `&`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTSC
    -0.58
    [];
    -0.55
    [][]
    -0.55
     Arrondissement
    -0.49
     ??????
    -0.48
    #
    -0.48
     <=",
    -0.48
    bitat
    -0.48
    SqlSession
    -0.47
    Спасылкі
    -0.47
    POSITIVE LOGITS
    &
    1.37
     &
    1.16
    &,
    1.01
    &&
    0.93
    >&
    0.92
    \&
    0.92
    &)
    0.92
    }&
    0.89
    "&
    0.88
    '&
    0.87
    Act Density 0.196%

    No Known Activations