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

    Neuronpedia

    INDEX
    Explanations

    duration and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.89
    8
    0.84
    6
    0.82
     toilet
    0.76
     million
    0.67
     thousands
    0.66
    quoia
    0.65
    9
    0.65
     asper
    0.64
     camshaft
    0.64
    POSITIVE LOGITS
     )-
    0.72
     stries
    0.70
    testAvg
    0.69
    ).-
    0.69
    ).—
    0.68
     هذ
    0.67
    tempCard
    0.67
     प्रश्‍न
    0.67
    Ellen
    0.66
    ParentElement
    0.66
    Act Density 0.273%

    No Known Activations