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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and commas in source code snippets

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ”,
    -1.23
    ".
    -1.16
    )".
    -1.12
    “,
    -1.08
    ".
    -1.04
    ”.
    -1.02
    ",
    -1.02
    !".
    -1.00
    !",
    -0.99
    )",
    -0.98
    POSITIVE LOGITS
    GEBURTSDATUM
    0.84
    '
    0.76
    ?
    0.71
    ’
    0.62
     ProtoMessage
    0.59
    0.56
    EndContext
    0.55
    <bos>
    0.52
    ↵↵
    0.51
    Билгалдахарш
    0.51
    Act Density 0.893%
    No Known Activations