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

    Neuronpedia

    INDEX
    Explanations

    comprehending literary and everyday texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Texte
    0.85
    роз
    0.83
     Composition
    0.83
     compositions
    0.81
    Pieces
    0.79
     conservación
    0.78
    composition
    0.78
     pieces
    0.77
     compreensão
    0.77
     Pieces
    0.77
    POSITIVE LOGITS
    ค่า
    0.69
     dens
    0.68
     main
    0.62
    aski
    0.61
     specials
    0.58
     theme
    0.58
     unten
    0.57
     ribs
    0.57
     اصلي
    0.57
     meno
    0.57
    Act Density 0.032%

    No Known Activations