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

    Neuronpedia

    INDEX
    Explanations

    performance best/better/less approximation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waveguides
    0.44
     cylindrical
    0.44
     using
    0.41
     your
    0.40
     utilizzando
    0.39
     hứng
    0.38
     utilizzare
    0.38
    നാണ്
    0.38
     mỗi
    0.38
     사용하는
    0.38
    POSITIVE LOGITS
     размеры
    0.59
     Sizes
    0.48
     サイズ
    0.47
     результат
    0.46
     sizes
    0.45
     варианты
    0.43
    hezza
    0.40
     Größen
    0.40
     உள்ளன
    0.39
     Small
    0.39
    Act Density 0.002%

    No Known Activations