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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Calculate
    -0.07
     값
    -0.06
     Flower
    -0.06
    _ob
    -0.06
     Component
    -0.06
     goat
    -0.06
     Protestant
    -0.06
     Tabs
    -0.06
     部
    -0.06
     Particularly
    -0.06
    POSITIVE LOGITS
    -sur
    0.07
     ماد
    0.07
     wyn
    0.06
     edilm
    0.06
    γραφ
    0.06
    圳
    0.06
    /books
    0.06
     ir
    0.06
    .Async
    0.06
    handling
    0.06
    Act Density 0.006%

    No Known Activations