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

    Neuronpedia

    INDEX
    Explanations

    equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    общи
    -0.07
     PageInfo
    -0.07
    冷笑
    -0.07
    历史新高
    -0.07
     grips
    -0.07
     tightening
    -0.06
     Prev
    -0.06
    UnitOfWork
    -0.06
    寻常
    -0.06
    wx
    -0.06
    POSITIVE LOGITS
    .Bar
    0.07
    颁布
    0.07
    pring
    0.07
    >s
    0.07
     pole
    0.07
    どの
    0.07
     Dal
    0.07
     הקר
    0.06
     Uses
    0.06
     والس
    0.06
    Act Density 0.034%

    No Known Activations