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

    Neuronpedia

    INDEX
    Explanations

    (-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avez
    -0.08
    /table
    -0.07
     것을
    -0.07
    for
    -0.07
     가정
    -0.07
     DateFormatter
    -0.07
    rijk
    -0.07
     Past
    -0.07
    해서
    -0.07
     Armour
    -0.07
    POSITIVE LOGITS
     inclus
    0.07
     бел
    0.06
     consequential
    0.06
    $PostalCodesNL
    0.06
     Edu
    0.06
    ávající
    0.06
     venir
    0.06
    =(-
    0.06
    少年
    0.06
    _ads
    0.06
    Act Density 0.003%

    No Known Activations