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

    Neuronpedia

    INDEX
    Explanations

    description or overview of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    すべて
    0.45
    쪽에
    0.42
    定める
    0.40
     annoying
    0.40
    ann
    0.38
     ramb
    0.38
     slings
    0.36
     slugs
    0.36
    იდან
    0.36
    િં
    0.36
    POSITIVE LOGITS
     of
    1.45
    នៃ
    1.31
     של
    1.30
     ofthe
    1.28
     của
    1.27
    ของการ
    1.27
     của
    1.19
    ของ
    1.13
    of
    1.00
    ຂອງ
    0.99
    Act Density 0.011%

    No Known Activations