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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GameOver
    -0.07
     řízení
    -0.06
    Employee
    -0.06
    皇
    -0.06
     lúc
    -0.06
     exhibitions
    -0.06
    采购
    -0.06
     nin
    -0.06
    uppet
    -0.06
    =torch
    -0.06
    POSITIVE LOGITS
    وات
    0.07
     resolved
    0.07
    znam
    0.07
     thaw
    0.07
     ود
    0.06
     intuitive
    0.06
     deals
    0.06
    .metadata
    0.06
     ú
    0.06
    aggi
    0.06
    Act Density 0.049%

    No Known Activations