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

    Neuronpedia

    INDEX
    Explanations

    Political/controversial discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     túi
    -0.07
    有关
    -0.07
    طم
    -0.07
     lớp
    -0.07
     alles
    -0.07
     đột
    -0.06
    'ai
    -0.06
     MOZ
    -0.06
     Quảng
    -0.06
    <Game
    -0.06
    POSITIVE LOGITS
    William
    0.06
    block
    0.06
    .where
    0.06
    ↵
    0.06
    leftrightarrow
    0.06
    FORMATION
    0.06
    _notification
    0.06
     dictionary
    0.06
     Betty
    0.06
    ,
↵
    0.06
    Act Density 0.009%

    No Known Activations