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

    Neuronpedia

    INDEX
    Explanations

    shapes and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.68
    se
    0.61
    is
    0.59
    ните
    0.59
    не
    0.57
     фильмы
    0.57
    리
    0.57
     चिह्न
    0.54
     বৃদ্ধি
    0.54
    ριν
    0.54
    POSITIVE LOGITS
     cylindrical
    0.64
     Shape
    0.57
     shape
    0.57
     cylinder
    0.56
     cylinders
    0.56
    Shape
    0.53
     r
    0.53
     mumbai
    0.49
     geometria
    0.49
    AY
    0.47
    Act Density 0.186%

    No Known Activations