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

    Neuronpedia

    INDEX
    Explanations

    Disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cập
    -0.07
     guilt
    -0.07
    ρά
    -0.07
     advising
    -0.07
    اویر
    -0.07
    Africa
    -0.06
    é
    -0.06
    ographically
    -0.06
    üt
    -0.06
    _Db
    -0.06
    POSITIVE LOGITS
     visc
    0.06
     سیاسی
    0.06
     biopsy
    0.06
     organizace
    0.06
    *X
    0.06
     onions
    0.06
    ヽ
    0.06
     verdienen
    0.06
    (SDL
    0.06
     reminiscent
    0.06
    Act Density 0.011%

    No Known Activations