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

    Neuronpedia

    INDEX
    Explanations

    class __init__

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ન
    1.19
    ด์
    1.16
     dov
    1.16
    ik
    1.04
     unsurpassed
    1.03
    aj
    1.02
     قلنا
    1.01
    ach
    1.00
     właśnie
    0.99
    posal
    0.98
    POSITIVE LOGITS
    िशनर
    1.17
    ുന്ന
    1.08
    ibfk
    1.05
     طريق
    1.04
     metallurgy
    1.02
    locator
    1.02
    凵
    0.98
     discrepancy
    0.96
    ρου
    0.96
    ными
    0.96
    Act Density 0.003%

    No Known Activations