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

    Neuronpedia

    INDEX
    Explanations

    in the same way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ntawm
    0.68
    泥
    0.67
    iris
    0.66
    ريض
    0.66
    ခြေ
    0.65
     থাকলে
    0.64
    screens
    0.62
    чених
    0.62
    국의
    0.61
     amines
    0.61
    POSITIVE LOGITS
     way
    5.26
     Way
    4.12
    Way
    4.10
    way
    3.86
     WAY
    3.85
    WAY
    3.43
     ways
    3.42
     manière
    3.16
     manera
    3.16
     manier
    3.07
    Act Density 0.307%

    No Known Activations