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

    Neuronpedia

    INDEX
    Explanations

    functor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isActive
    -0.07
    ương
    -0.06
    008
    -0.06
    codigo
    -0.06
     awesome
    -0.06
    planation
    -0.06
    752
    -0.06
     rat
    -0.06
    aram
    -0.06
    aar
    -0.06
    POSITIVE LOGITS
     هزار
    0.07
    _modifier
    0.07
     functor
    0.07
    圖
    0.07
    σουν
    0.07
     uměl
    0.06
     конкур
    0.06
     Functor
    0.06
     공고
    0.06
     هند
    0.06
    Act Density 0.002%

    No Known Activations