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

    Neuronpedia

    INDEX
    Explanations

    URL endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ・
    0.83
    Product
    0.76
    产品
    0.74
     ધ્યા
    0.74
     meninas
    0.74
     রাস্তা
    0.73
    演员
    0.70
    เรียก
    0.69
     Producto
    0.69
     Produits
    0.68
    POSITIVE LOGITS
     final
    0.82
     go
    0.73
    .)
    0.70
    :\
    0.68
    :}
    0.68
    .&
    0.67
     .)
    0.67
     tests
    0.67
     projections
    0.67
     mock
    0.65
    Act Density 0.022%

    No Known Activations