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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .option
    -0.08
    (IO
    -0.07
     propel
    -0.07
    Nick
    -0.07
    (QL
    -0.07
    |`↵
    -0.06
    _tex
    -0.06
    .fore
    -0.06
    [input
    -0.06
    (PATH
    -0.06
    POSITIVE LOGITS
    ::*;↵
    0.07
    郑
    0.07
    厂房
    0.07
    此時
    0.07
     emptied
    0.07
    散文
    0.07
     Samantha
    0.06
     Libre
    0.06
    .GetFiles
    0.06
    的文字
    0.06
    Act Density 0.001%

    No Known Activations