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

    Neuronpedia

    INDEX
    Explanations

    coding and programming concepts, particularly related to data types and structures

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

    code delimiters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.80
     Wikiseite
    -0.78
    ########.
    -0.75
    %")
    -0.70
     wikipagina
    -0.69
    __":
    -0.66
    %");
    -0.66
     betweenstory
    -0.65
    CloseOperation
    -0.64
    ')")
    -0.64
    POSITIVE LOGITS
    ,
    0.58
    .
    0.57
    ;
    0.53
     again
    0.44
    .,
    0.40
    :
    0.38
     ,
    0.38
    astéroïdes
    0.36
     ролях
    0.34
    !
    0.34
    Act Density 0.019%

    No Known Activations