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

    Neuronpedia

    INDEX
    Explanations

    上下

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েব
    0.37
     гра
    0.37
    рети
    0.37
     Анаста
    0.37
    satunya
    0.37
    हेब
    0.36
     беру
    0.36
     Avent
    0.36
     গ্র
    0.35
    aar
    0.35
    POSITIVE LOGITS
    此事
    0.46
     aspect
    0.38
    ygons
    0.38
     defe
    0.38
     যেগুলো
    0.38
    則是
    0.38
     locals
    0.38
    udas
    0.38
    Aspect
    0.38
     disa
    0.38
    Act Density 0.000%

    No Known Activations