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

    Neuronpedia

    INDEX
    Explanations

    relative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للإ
    -0.08
    iffel
    -0.08
     mágico
    -0.08
    sets
    -0.08
     मश
    -0.07
     metabolic
    -0.07
     magique
    -0.07
     trang
    -0.07
     homicide
    -0.07
     بش
    -0.07
    POSITIVE LOGITS
    .Order
    0.11
    -order
    0.11
     order
    0.11
     alphabetical
    0.11
     untouched
    0.11
    (Order
    0.10
     ترتيب
    0.10
     порядок
    0.10
     preserved
    0.10
    order
    0.10
    Act Density 0.007%

    No Known Activations