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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conf
    -0.06
    чим
    -0.06
    lfw
    -0.06
    ğiniz
    -0.06
    едагог
    -0.06
    -warning
    -0.06
    _pages
    -0.06
     TESTING
    -0.06
    227
    -0.06
    view
    -0.06
    POSITIVE LOGITS
     žádný
    0.07
     azimuth
    0.06
    Imm
    0.06
    inkel
    0.06
     forb
    0.06
    τωση
    0.06
     Laws
    0.06
     ({↵
    0.06
     psz
    0.06
     estable
    0.06
    Act Density 0.041%

    No Known Activations