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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of uncertainty

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

    questions involving thoughts or contemplative reasoning

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

    What follows punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ungeon
    -0.77
    __":
    -0.71
    __':
    -0.67
     />";
    -0.65
    />";
    -0.65
     AssemblyTitle
    -0.65
     yourselves
    -0.64
    aksikan
    -0.64
    ⋙
    -0.64
     Вікіпе
    -0.62
    POSITIVE LOGITS
     thoughts
    0.74
     Suddenly
    0.73
    Suddenly
    0.70
    Thinking
    0.69
     thought
    0.64
    ふと
    0.64
     suddenly
    0.63
     Maybe
    0.63
    Maybe
    0.62
     thinking
    0.62
    Act Density 0.049%

    No Known Activations