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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     essen
    -0.08
     magazines
    -0.07
     selling
    -0.06
     stations
    -0.06
     frying
    -0.06
     보
    -0.06
    лених
    -0.06
    1
    -0.06
     guy
    -0.06
    opoly
    -0.06
    POSITIVE LOGITS
     seventh
    0.11
     sixth
    0.11
     fifth
    0.10
    th
    0.10
     eighth
    0.09
    ifth
    0.08
     Fifth
    0.08
     Seventh
    0.08
     Sixth
    0.08
     tph
    0.08
    Act Density 0.060%

    No Known Activations