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

    Neuronpedia

    INDEX
    Explanations

    Ordinal suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     targeting
    -0.06
    *)(
    -0.06
    ameron
    -0.06
    *X
    -0.06
    idir
    -0.06
     Cassidy
    -0.06
    ylim
    -0.06
     acompanh
    -0.06
     vigilant
    -0.05
    elsius
    -0.05
    POSITIVE LOGITS
    th
    0.09
     أول
    0.07
    -st
    0.07
     SM
    0.07
     loading
    0.07
    celed
    0.07
    ).'</
    0.07
    TH
    0.07
     readme
    0.07
    だった
    0.07
    Act Density 0.033%

    No Known Activations