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

    Neuronpedia

    INDEX
    Explanations

    excellent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MEMORY
    -0.07
     SORT
    -0.07
    atör
    -0.07
    _VIS
    -0.07
    -go
    -0.07
    pirit
    -0.07
     галуз
    -0.07
     site
    -0.07
     territor
    -0.06
    olocation
    -0.06
    POSITIVE LOGITS
     excellent
    0.16
     Excellent
    0.11
    Excellent
    0.10
     excell
    0.08
    cellent
    0.08
    ICollectionView
    0.07
    Glass
    0.07
     Joel
    0.07
     εξ
    0.07
    est
    0.07
    Act Density 0.007%

    No Known Activations