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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Approx
    -0.06
    次
    -0.06
    Five
    -0.06
    aspect
    -0.06
     machine
    -0.06
     yukarı
    -0.06
     injuring
    -0.06
    ooting
    -0.06
     undergoing
    -0.06
    ptom
    -0.06
    POSITIVE LOGITS
     kam
    0.08
     caring
    0.07
     USART
    0.06
     mol
    0.06
    Calendar
    0.06
     ain
    0.06
    [::-
    0.06
     ikea
    0.06
    :SetPoint
    0.06
     fint
    0.06
    Act Density 0.055%

    No Known Activations