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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references in the text

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

    Hexadecimal characters and numbers mixed in strings

    np_acts-logits-general · gemini-2.0-flash

    for loop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -1.41
    )";
    -1.38
    )"),
    -1.37
    )");
    -1.32
     AssemblyCulture
    -1.31
     >",
    -1.19
     useAppContext
    -1.19
    parsedMessage
    -1.19
    ".
    -1.18
    writeFieldEnd
    -1.16
    POSITIVE LOGITS
    _
    1.32
    .
    1.15
    /
    1.00
    -
    0.91
     -
    0.86
    __
    0.81
    _{
    0.79
    \_
    0.79
     _
    0.78
    ._
    0.77
    Act Density 0.141%

    No Known Activations