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

    Neuronpedia

    INDEX
    Explanations

    famous writers and artists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    1.09
    म
    0.82
    د
    0.79
     or
    0.73
     nets
    0.73
    ش
    0.73
     has
    0.73
     plana
    0.73
    д
    0.72
     Magento
    0.69
    POSITIVE LOGITS
    も
    0.85
    도
    0.80
    ও
    0.73
     və
    0.72
     جہاں
    0.72
    *[
    0.70
    튬
    0.67
    もあった
    0.64
    কে
    0.64
    unately
    0.64
    Act Density 0.000%

    No Known Activations