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

    Neuronpedia

    INDEX
    Explanations

    o

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sm
    -0.07
    圣地
    -0.07
    List
    -0.07
    €
    -0.06
    [List
    -0.06
    _continue
    -0.06
    ($(".
    -0.06
    ˘
    -0.06
    _sms
    -0.06
    _hidden
    -0.06
    POSITIVE LOGITS
     Mona
    0.07
    -rays
    0.07
    发烧
    0.07
    /ext
    0.07
     setups
    0.07
    oneksi
    0.07
    逼
    0.07
     Auf
    0.07
     Copy
    0.07
    .chdir
    0.07
    Act Density 0.001%

    No Known Activations