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

    Neuronpedia

    INDEX
    Explanations

    through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.99
    ן
    0.90
    .
    0.84
    서
    0.79
    ’.
    0.78
    ‌ها
    0.75
    is
    0.74
    нием
    0.72
    ,
    0.72
    א
    0.71
    POSITIVE LOGITS
    kha
    0.91
     وبعد
    0.77
    kang
    0.75
    過程
    0.75
     وبين
    0.75
     injective
    0.75
    kook
    0.74
    শনাল
    0.74
    RxDocument
    0.73
    kých
    0.72
    Act Density 0.482%

    No Known Activations