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

    Neuronpedia

    INDEX
    Explanations

    terms related to parsing and parsed objects

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

    parsing structured data and text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.38
    engaruhi
    -0.36
    <h4>
    -0.36
    ilangkan
    -0.35
    Referències
    -0.35
     cạnh
    -0.35
     Whyte
    -0.35
    kenstock
    -0.35
    <bos>
    -0.34
     mecan
    -0.34
    POSITIVE LOGITS
    parsed
    2.00
     parsed
    1.98
    Parsed
    1.57
     Parsing
    0.96
     parsing
    0.91
    parsing
    0.90
     processed
    0.82
    parsedMessage
    0.82
    Parsing
    0.82
     decoded
    0.81
    Act Density 0.007%

    No Known Activations