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

    Neuronpedia

    INDEX
    Explanations

    vibrant scenes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (boost
    -0.07
    .fixed
    -0.07
    (split
    -0.07
     outputFile
    -0.06
     král
    -0.06
     trout
    -0.06
     UICollectionView
    -0.06
     releases
    -0.06
     costly
    -0.06
     styling
    -0.06
    POSITIVE LOGITS
     Affairs
    0.07
     масла
    0.07
     pretend
    0.06
     vibrant
    0.06
     mornings
    0.06
     Sect
    0.06
    ;b
    0.06
    -market
    0.06
    .table
    0.06
    /dev
    0.06
    Act Density 0.012%

    No Known Activations