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

    Neuronpedia

    INDEX
    Explanations

    references to government officials and their relationships

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

    Punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    logic & punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ")){
    -0.86
    yntaxException
    -0.83
    （）
    -0.78
     */;
    -0.75
    ")]
    -0.74
     {}'.
    -0.73
    >");
    -0.72
    ''',
    -0.72
    <bos>
    -0.72
    "):
    -0.72
    POSITIVE LOGITS
     &
    1.14
     (&
    0.80
     \&
    0.74
    /
    0.71
     (=
    0.71
     yrs
    0.69
     !?
    0.69
     !!
    0.69
     aka
    0.69
     !!!
    0.68
    Act Density 0.438%

    No Known Activations