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

    Neuronpedia

    INDEX
    Explanations

    gaining popularity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    not
    0.80
    。
    0.77
    ry
    0.70
    iden
    0.68
    star
    0.68
    ।
    0.68
    res
    0.67
    night
    0.66
    array
    0.66
    ned
    0.66
    POSITIVE LOGITS
    é
    0.79
     revolutionize
    0.77
     THE
    0.75
     popularity
    0.75
     to
    0.73
     लोकप्रियता
    0.71
    ু
    0.69
     IVA
    0.66
     centralization
    0.65
     использования
    0.65
    Act Density 0.004%

    No Known Activations