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

    Neuronpedia

    INDEX
    Explanations

    encode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     element
    -0.08
     twig
    -0.08
    ंद
    -0.07
     StringBuilder
    -0.07
    .mode
    -0.07
    系統
    -0.07
     innovations
    -0.06
     Alan
    -0.06
     Units
    -0.06
    wie
    -0.06
    POSITIVE LOGITS
    翔
    0.07
    [u
    0.06
    原
    0.06
    depart
    0.06
    density
    0.06
    URLConnection
    0.06
    _PREF
    0.06
    _chg
    0.06
     Hamm
    0.06
    DY
    0.06
    Act Density 0.004%

    No Known Activations