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

    Neuronpedia

    INDEX
    Explanations

    operator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     refill
    -0.07
     список
    -0.07
    _All
    -0.07
    冲洗
    -0.07
     Begins
    -0.07
    开启
    -0.07
    AGEMENT
    -0.07
    __
    -0.07
    了些
    -0.07
    stoff
    -0.06
    POSITIVE LOGITS
     the
    0.07
     a
    0.07
     and
    0.07
     rapes
    0.07
    linha
    0.07
    erto
    0.07
     operators
    0.07
     airl
    0.07
    ा�
    0.06
    acz
    0.06
    Act Density 0.011%

    No Known Activations