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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in a text

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

    Text preceding less common words

    np_acts-logits-general · gemini-2.0-flash

    foreign characters and technical code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Amicalement
    -0.61
    最快更新
    -0.56
    ulkan
    -0.56
    illaume
    -0.54
    sandal
    -0.54
    Спасибо
    -0.49
     tassels
    -0.49
    شكرا
    -0.48
    fishes
    -0.48
     StatefulWidget
    -0.48
    POSITIVE LOGITS
    UnusedPrivate
    0.65
    awtextra
    0.63
     فريبيس
    0.59
     nakalista
    0.58
    AntiForgeryToken
    0.54
    InjectAttribute
    0.53
    cupa
    0.53
    ;#
    0.51
     autorytatywna
    0.50
     stagger
    0.49
    Act Density 0.008%

    No Known Activations