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

    Neuronpedia

    INDEX
    Explanations

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zero
    0.77
     ۸
    0.75
     ८
    0.75
     ۳
    0.70
     ۷
    0.69
     Metaverse
    0.69
     ٣
    0.67
     ७
    0.67
     ۴
    0.67
     ९
    0.66
    POSITIVE LOGITS
    1
    1.41
    <unused1857>
    0.78
    १८
    0.75
    ១
    0.74
    <unused1999>
    0.74
    <unused1190>
    0.74
    ১৬
    0.73
    ૧
    0.72
    ১৫
    0.71
    ۱۳
    0.71
    Act Density 0.052%

    No Known Activations