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

    Neuronpedia

    INDEX
    Explanations

    layout definitions and content types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Preparazione
    -0.94
     ответы
    -0.87
     تمثيل
    -0.87
    διά
    -0.86
     Gewichts
    -0.86
     tremendous
    -0.85
    ebly
    -0.85
     eindeutig
    -0.84
     magnificent
    -0.84
     astounding
    -0.84
    POSITIVE LOGITS
     after
    1.05
     five
    0.82
     what
    0.81
     nestled
    0.80
     main
    0.79
     Marino
    0.79
     Airport
    0.78
     notific
    0.77
     weirdly
    0.76
     tiendas
    0.75
    Act Density 0.006%

    No Known Activations