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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     docs
    -0.07
     Soul
    -0.07
    Rows
    -0.06
     Sour
    -0.06
    %,
    -0.06
     않은
    -0.06
    CORE
    -0.06
    (date
    -0.06
    Yu
    -0.06
    binding
    -0.06
    POSITIVE LOGITS
    (UnmanagedType
    0.07
     Salon
    0.07
     Robotics
    0.06
    оск
    0.06
     boş
    0.06
     Comparator
    0.06
    xac
    0.06
     suited
    0.06
     Ін
    0.06
     örg
    0.06
    Act Density 0.002%

    No Known Activations