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

    Neuronpedia

    INDEX
    Explanations

    closing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    奇特
    -0.08
    routing
    -0.07
     empire
    -0.07
    ientras
    -0.07
     militants
    -0.07
     لأ
    -0.07
     stunned
    -0.07
     En
    -0.06
     bagi
    -0.06
    情节
    -0.06
    POSITIVE LOGITS
    _Log
    0.07
    _least
    0.07
    _quit
    0.07
    Alive
    0.07
    局限
    0.07
     hiç
    0.07
    ,left
    0.07
    促进了
    0.06
    abcdefghijkl
    0.06
    积极作用
    0.06
    Act Density 0.012%

    No Known Activations