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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gemini-2.0-flash

    Separators (/, dates, etc.)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.67
     дописавши
    -0.65
    }{*}{
    -0.63
     ")"
    -0.60
    ("}");
    -0.59
     InputDecoration
    -0.59
    Jeografia
    -0.59
    ărat
    -0.58
    ']],
    -0.58
    ContentAsync
    -0.56
    POSITIVE LOGITS
    <bos>
    1.16
     October
    0.73
     December
    0.72
     February
    0.69
     January
    0.68
     July
    0.68
     April
    0.68
     September
    0.68
    December
    0.67
    February
    0.67
    Act Density 0.753%

    No Known Activations