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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    主管
    -0.08
    efte
    -0.08
     प्रक
    -0.08
     өй
    -0.08
     anonymous
    -0.08
    Segoe
    -0.08
    hei
    -0.08
     anemia
    -0.08
    �
    -0.08
     Italiano
    -0.07
    POSITIVE LOGITS
     changed
    0.08
     Gh
    0.07
     casually
    0.07
    Cas
    0.07
    {Name
    0.07
    _ENV
    0.07
     dividing
    0.07
     Hugh
    0.07
     divert
    0.07
    다는
    0.06
    Act Density 0.000%

    No Known Activations