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

    Neuronpedia

    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compl
    -0.07
     있을
    -0.06
     리
    -0.06
     UIScreen
    -0.06
     пти
    -0.06
     mrt
    -0.06
     Kee
    -0.06
    eli
    -0.06
    'Connor
    -0.06
     кто
    -0.06
    POSITIVE LOGITS
     Dawn
    0.07
    .frames
    0.07
    ;\
    0.07
     [...]↵↵
    0.07
     number
    0.06
     journalism
    0.06
    hip
    0.06
     जल
    0.06
     four
    0.06
     Sep
    0.06
    Act Density 0.024%

    No Known Activations