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

    Neuronpedia

    INDEX
    Explanations

    lines that start a unit test in Javascript

    oai_token-act-pair · gemini-2.0-flash

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -0.97
    TintMode
    -0.81
     Paglinawan
    -0.71
    ьаж
    -0.67
    igshid
    -0.66
     Италијани
    -0.65
     فريبيس
    -0.64
    ValueGenerated
    -0.62
    참고
    -0.59
    Abitanti
    -0.57
    POSITIVE LOGITS
    omiast
    0.52
    styleType
    0.51
    ()]);
    0.48
    hawatir
    0.47
    <bos>
    0.45
     }}}
    0.45
    :],
    0.45
    تفسير
    0.44
     Erb
    0.44
    ضايا
    0.44
    Act Density 0.208%

    No Known Activations