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

    Neuronpedia

    INDEX
    Explanations

    code constructs and data structure references related to packed and fixed data types

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

    ".packed" or ".repeated" followed by a data type

    np_acts-logits-general · gemini-2.0-flash

    repeated or packed types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.73
    ,
    -0.72
     
    -0.68
    ?
    -0.67
    <eos>
    -0.62
     T
    -0.61
     /
    -0.60
      
    -0.59
    -
    -0.59
    .
    -0.58
    POSITIVE LOGITS
    RenderAtEndOf
    1.03
    脚注の使い方
    0.89
    ArgsConstructor
    0.87
     ComVisible
    0.83
     EconPapers
    0.82
     becauſe
    0.81
     مشين
    0.80
     ―――――
    0.79
     Theſe
    0.78
     ―――
    0.78
    Act Density 0.256%

    No Known Activations