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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks and formatting elements in text

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

    Code or programming syntax

    np_acts-logits-general · gemini-2.0-flash

    code syntax and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ----------------
    -0.45
    茉
    -0.43
    ***
    -0.38
    En
    -0.38
    тера
    -0.37
    **
    -0.37
     sot
    -0.36
    nb
    -0.36
    local
    -0.36
    aka
    -0.36
    POSITIVE LOGITS
    __':
    1.14
     Normdatei
    1.04
    __":
    0.99
     AssemblyCulture
    0.97
    __':
    0.93
    ’.”
    0.92
    CloseOperation
    0.91
    ."],
    0.89
    .)}
    0.88
    '],
    0.88
    Act Density 0.127%

    No Known Activations