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

    Neuronpedia

    INDEX
    Explanations

    HTML code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >
    0.92
    inidad
    0.69
    isiones
    0.69
    ToBounds
    0.66
    менять
    0.65
    ኘት
    0.63
    ‌شده
    0.62
    ಿಕ
    0.62
    inement
    0.62
    ivität
    0.61
    POSITIVE LOGITS
     ما
    0.76
    글
    0.75
     Weiss
    0.72
     Illustrations
    0.71
    唕
    0.70
     글
    0.70
     이
    0.69
    সু
    0.68
     raster
    0.68
     द्वारा
    0.68
    Act Density 0.032%

    No Known Activations