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

    Neuronpedia

    INDEX
    Explanations

    our scientific and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.78
    يني
    0.77
    haltens
    0.74
    isis
    0.73
     niiden
    0.72
     suivantes
    0.71
     dniu
    0.69
    ento
    0.68
     akár
    0.68
    危害
    0.68
    POSITIVE LOGITS
     нашим
    1.37
     нашего
    1.29
     ನಮ್ಮ
    1.27
     наших
    1.25
     нашей
    1.23
     naš
    1.23
     vores
    1.22
     наши
    1.19
     наш
    1.19
     beloved
    1.18
    Act Density 0.041%

    No Known Activations