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

    Neuronpedia

    INDEX
    Explanations

    containers and concurrent operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viết
    0.39
    纽
    0.39
    stüt
    0.37
    jo
    0.37
    DEFGHIJKLMNOP
    0.37
     commodity
    0.36
    뉘
    0.36
     प्रोड
    0.35
     extrem
    0.35
     j
    0.35
    POSITIVE LOGITS
    Container
    0.44
     gradually
    0.43
     Container
    0.42
     container
    0.41
     concurrency
    0.41
     ঘনত্ব
    0.41
    PerRow
    0.40
    container
    0.40
    Listener
    0.40
     concurrent
    0.39
    Act Density 0.002%

    No Known Activations