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

    Neuronpedia

    INDEX
    Explanations

    text in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    code/copyright notices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.23
    numerusform
    -0.78
     autorytatywna
    -0.70
    Rüyada
    -0.64
    ⓧ
    -0.60
    featureID
    -0.59
    Билгалдахарш
    -0.58
    copyWith
    -0.58
    Autoritní
    -0.55
    لينكات
    -0.54
    POSITIVE LOGITS
    ."</
    0.78
    "</
    0.70
    ".
    0.69
    ValueStyle
    0.58
     "¡
    0.57
     MainAxisSize
    0.57
    moiselle
    0.55
    )”.
    0.54
     "\<
    0.54
    !!</
    0.52
    Act Density 1.495%

    No Known Activations