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

    Neuronpedia

    INDEX
    Explanations

    numeric suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Какой
    1.07
     reclama
    0.86
    es
    0.85
     Creations
    0.80
     Consult
    0.77
     Eds
    0.77
     Cz
    0.76
     apuesta
    0.76
     agrade
    0.76
     Catalogue
    0.75
    POSITIVE LOGITS
    ма
    0.95
    UEFA
    0.86
    უნქ
    0.82
    사를
    0.81
    。<
    0.81
    र्नर
    0.81
     역할을
    0.80
     eprintln
    0.80
    RefIn
    0.80
    ום
    0.78
    Act Density 0.002%

    No Known Activations