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

    Neuronpedia

    INDEX
    Explanations

    physical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UserRole
    -0.06
     Tổ
    -0.06
     ngủ
    -0.06
     času
    -0.06
    巧
    -0.06
     tavs
    -0.06
     McCain
    -0.06
    又
    -0.06
     Trader
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    ological
    0.06
     lateral
    0.06
    .color
    0.06
    LONG
    0.06
     distinguish
    0.06
     động
    0.06
    }{↵
    0.06
     auxiliary
    0.06
     ],↵
    0.06
     nid
    0.06
    Act Density 0.009%

    No Known Activations