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

    Neuronpedia

    INDEX
    Explanations

    instances of closing curly braces in code snippets

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

    foreign words and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.64
     незавершена
    -0.59
    oa̍t
    -0.59
     surla
    -0.57
    expandindo
    -0.52
    TagMode
    -0.50
    BeginContext
    -0.50
     oprot
    -0.48
    Chham
    -0.48
     CanadaChoose
    -0.45
    POSITIVE LOGITS
    BibitemShut
    0.45
     Grüsse
    0.45
    protoimpl
    0.43
     poudre
    0.42
     argint
    0.40
     مبارک
    0.39
     useCallback
    0.39
    taget
    0.36
    //});
    0.35
     carreteras
    0.35
    Act Density 0.021%

    No Known Activations