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

    Neuronpedia

    INDEX
    Explanations

    instances of negation or contradiction in statements

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

    Punctuation followed by numbers or specific letters

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TextBoxColumn
    -0.66
    DoubleQuotes
    -0.60
    :✨
    -0.57
    Välislingid
    -0.57
    siella
    -0.56
     {,
    -0.56
     pasangan
    -0.53
     насељу
    -0.52
    corresponding
    -0.50
    leste
    -0.49
    POSITIVE LOGITS
    setVerticalGroup
    0.61
    发表于
    0.58
     collectivités
    0.56
     Normdatei
    0.54
     NSCoder
    0.54
    zzleHttp
    0.53
    Third
    0.53
    YOND
    0.52
     Third
    0.51
     newOwner
    0.51
    Act Density 0.340%

    No Known Activations