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

    Neuronpedia

    INDEX
    Explanations

    filtering data based on conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    岫
    0.45
     মিটিং
    0.43
    리와
    0.42
     দীননাথ
    0.41
    Ე
    0.41
     можа
    0.40
    inars
    0.40
    Brexit
    0.40
    ୍ର
    0.39
     Managed
    0.39
    POSITIVE LOGITS
     digo
    0.42
    iletto
    0.42
     a
    0.41
     to
    0.40
     yani
    0.39
     cannot
    0.39
     गटा
    0.39
     pocos
    0.39
     two
    0.38
     center
    0.38
    Act Density 0.015%

    No Known Activations