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

    Neuronpedia

    INDEX
    Explanations

    formatting/tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sequences
    -0.08
    (div
    -0.08
     Spa
    -0.08
    ஸ
    -0.07
    spark
    -0.07
     perpetual
    -0.07
     pats
    -0.07
     trava
    -0.07
    स्कार
    -0.07
     equivoc
    -0.07
    POSITIVE LOGITS
     Над
    0.08
     تعريف
    0.08
    支
    0.08
     Ө
    0.07
     Основ
    0.07
     ಉದ್ಯ
    0.07
    cte
    0.07
     Наш
    0.07
     Pretty
    0.07
     المخ
    0.07
    Act Density 0.082%

    No Known Activations