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

    Neuronpedia

    INDEX
    Explanations

    program

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ederek
    -0.07
     عوامل
    -0.06
     catastrophic
    -0.06
     верх
    -0.06
     neue
    -0.06
     قط
    -0.06
    FINITE
    -0.06
    mada
    -0.06
    rita
    -0.06
    uir
    -0.06
    POSITIVE LOGITS
    shops
    0.07
    icable
    0.06
     dancing
    0.06
     successful
    0.06
     Pitt
    0.06
    ーリ
    0.06
     thrown
    0.06
     appealing
    0.06
    丰
    0.06
     Prices
    0.06
    Act Density 0.005%

    No Known Activations