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

    Neuronpedia

    INDEX
    Explanations

    elements of titles and categories

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

    the word "title"

    np_acts-logits-general · gemini-2.0-flash

    title and category labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.52
    FXMLLoader
    -0.51
    olescence
    -0.46
    kurat
    -0.44
    合
    -0.43
    ="#"><
    -0.43
    ="">
    -0.43
     immunos
    -0.42
     ensayos
    -0.42
     fisico
    -0.42
    POSITIVE LOGITS
    ніципалі
    0.69
     snippetHide
    0.68
    ]")]
    0.67
     Numerade
    0.64
    клопе
    0.64
     GenerationType
    0.62
     مشين
    0.61
    Title
    0.60
    +#+
    0.58
     gyhoeddwyd
    0.58
    Act Density 0.034%

    No Known Activations