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

    Neuronpedia

    INDEX
    Explanations

    Instructions or suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     are
    -0.09
     was
    -0.09
     will
    -0.09
     would
    -0.09
     be
    -0.08
     can
    -0.08
     is
    -0.08
     were
    -0.08
     been
    -0.08
     may
    -0.07
    POSITIVE LOGITS
     пой
    0.07
    .moveToNext
    0.06
    りに
    0.06
    lerle
    0.06
    ickt
    0.06
     самых
    0.06
    隊
    0.06
    TEAM
    0.06
     чоловік
    0.06
    .§
    0.06
    Act Density 0.197%

    No Known Activations