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

    Neuronpedia

    INDEX
    Explanations

    measurements in feet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     migraines
    1.48
     arteries
    1.45
     tassels
    1.41
     Nominal
    1.38
     HAL
    1.37
     weekdays
    1.37
     TIL
    1.37
     seasoned
    1.35
     aides
    1.35
    ן
    1.34
    POSITIVE LOGITS
    ING
    1.78
    м
    1.72
    Quando
    1.71
    и
    1.67
    হ
    1.66
    ۸
    1.62
     Algunos
    1.61
    building
    1.59
    know
    1.58
    ı
    1.58
    Act Density 0.032%

    No Known Activations