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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    งม
    -0.07
    ote
    -0.07
     beta
    -0.07
    edar
    -0.07
     enforcement
    -0.07
     rains
    -0.07
     кат
    -0.07
    Ethernet
    -0.06
    ewhere
    -0.06
     Brendan
    -0.06
    POSITIVE LOGITS
     wallpaper
    0.06
    умент
    0.06
    (find
    0.06
    래스
    0.06
    _ss
    0.06
    ています
    0.06
    -Col
    0.06
     snaží
    0.06
    ülük
    0.06
     이미지
    0.06
    Act Density 0.037%

    No Known Activations