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

    Neuronpedia

    INDEX
    Explanations

    magnetic vortices/monopoles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -east
    -0.06
     rượu
    -0.06
    ﱡ
    -0.06
     Extensions
    -0.06
    不肯
    -0.06
     MM
    -0.06
     kern
    -0.06
    ็น
    -0.06
     Mouth
    -0.06
    송
    -0.06
    POSITIVE LOGITS
    �
    0.07
    tık
    0.07
     między
    0.07
     simplement
    0.07
    ança
    0.07
    _bonus
    0.07
    ｂ
    0.07
    Alice
    0.07
     Bạn
    0.06
    [input
    0.06
    Act Density 0.002%

    No Known Activations