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

    Neuronpedia

    INDEX
    Explanations

    problems and inequities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interpolate
    0.84
     bekommt
    0.84
     제공
    0.82
     그냥
    0.82
    ന്റ
    0.82
     aktivieren
    0.78
     sicuramente
    0.78
     함수
    0.77
     做
    0.77
    훑
    0.75
    POSITIVE LOGITS
     inequities
    1.88
     disparities
    1.83
     inadequate
    1.81
     shortcomings
    1.77
     discrepancies
    1.72
     shortages
    1.67
     difficulties
    1.67
     lack
    1.66
     insufficient
    1.65
     mismanagement
    1.61
    Act Density 0.215%

    No Known Activations