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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vš
    -0.07
    erase
    -0.06
    ्भ
    -0.06
     groundwork
    -0.06
    ienia
    -0.06
     closed
    -0.06
    jet
    -0.06
     premise
    -0.06
    Closed
    -0.06
    cação
    -0.06
    POSITIVE LOGITS
     Seq
    0.07
     få
    0.06
     прот
    0.06
     향
    0.06
    (Customer
    0.06
     처음
    0.06
     qua
    0.06
    ))?
    0.06
    ूच
    0.06
    าก
    0.06
    Act Density 0.002%

    No Known Activations