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

    Neuronpedia

    INDEX
    Explanations

    first half

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dates
    0.69
    ृती
    0.69
     dates
    0.68
     rutas
    0.65
    dates
    0.65
    वर्षी
    0.65
     pathway
    0.64
     DAYS
    0.64
    ຖານ
    0.62
     Days
    0.62
    POSITIVE LOGITS
     hiệp
    1.21
     halves
    1.14
     half
    1.10
    HALF
    1.04
     regulation
    1.04
     Half
    1.02
    Half
    1.02
    上半
    0.99
     halftime
    0.99
    elapsed
    0.99
    Act Density 0.037%

    No Known Activations