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

    Neuronpedia

    INDEX
    Explanations

    j

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ONA
    -0.07
    (cd
    -0.07
    مض
    -0.07
     housed
    -0.07
    QS
    -0.06
    乾隆
    -0.06
    情趣
    -0.06
    $tmp
    -0.06
     Programme
    -0.06
    呐
    -0.06
    POSITIVE LOGITS
    .Unknown
    0.07
     escal
    0.07
     Kevin
    0.07
    方面
    0.07
    -eslint
    0.07
    _real
    0.07
     Kuala
    0.07
     Dear
    0.07
     Seiten
    0.07
     \$
    0.06
    Act Density 0.047%

    No Known Activations