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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (permission
    -0.07
     progresses
    -0.07
     avoided
    -0.06
     islands
    -0.06
    .visit
    -0.06
    navigator
    -0.06
    包
    -0.06
     transform
    -0.06
     Bought
    -0.06
    474
    -0.06
    POSITIVE LOGITS
     único
    0.07
    imedia
    0.07
    _variables
    0.06
     фут
    0.06
     labor
    0.06
     срок
    0.06
     cuales
    0.06
     سایت
    0.06
     kişisel
    0.06
     rowCount
    0.06
    Act Density 0.043%

    No Known Activations