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

    Neuronpedia

    INDEX
    Explanations

    functional programming operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initialization
    0.88
     displaying
    0.88
     methodName
    0.86
     initializing
    0.85
     관리
    0.81
     EventHandler
    0.81
     handels
    0.81
     Initialization
    0.80
     Establishing
    0.80
     สิ่ง
    0.80
    POSITIVE LOGITS
    clamp
    1.04
    map
    1.04
    reverse
    1.03
    filter
    1.03
    flatten
    1.01
    squeeze
    1.00
    flip
    0.99
    reduce
    0.98
    explode
    0.95
    intersect
    0.94
    Act Density 0.057%

    No Known Activations