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

    Neuronpedia

    INDEX
    Explanations

    can be, must be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oczywiście
    0.64
     says
    0.61
     tentunya
    0.59
     يقول
    0.57
     म्हणतात
    0.56
     creo
    0.55
     кажется
    0.54
    says
    0.54
     tentu
    0.53
     reportedly
    0.52
    POSITIVE LOGITS
     বুঝি
    0.58
     somehow
    0.57
     possa
    0.54
     possam
    0.51
     بتوان
    0.48
     pueda
    0.47
     nejen
    0.46
     possano
    0.45
    不仅
    0.44
    这是一
    0.44
    Act Density 0.198%

    No Known Activations