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

    Neuronpedia

    INDEX
    Explanations

    purchase and cashback links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    숫
    0.38
     ADMINISTRATION
    0.37
    艹
    0.36
    CTION
    0.35
    amı
    0.35
    اداسی
    0.34
     नियंत्रित
    0.34
    İŞ
    0.33
    وسیع
    0.33
     SALES
    0.33
    POSITIVE LOGITS
     Berkshire
    0.33
     Tra
    0.32
    Berk
    0.31
      
    0.30
     tri
    0.30
     atoms
    0.30
    这些
    0.30
     tra
    0.29
     unver
    0.29
     individual
    0.29
    Act Density 0.002%

    No Known Activations