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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cụ
    -0.07
     notably
    -0.07
     averaging
    -0.07
    סכם
    -0.07
    inski
    -0.07
     suis
    -0.07
     seul
    -0.06
     disaster
    -0.06
     pac
    -0.06
    mage
    -0.06
    POSITIVE LOGITS
     Malta
    0.08
    (to
    0.07
    _mas
    0.07
    Results
    0.07
     Returned
    0.07
     pros
    0.07
     armour
    0.06
     signings
    0.06
     tjejer
    0.06
    Origin
    0.06
    Act Density 0.031%

    No Known Activations