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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     国
    -0.07
     governance
    -0.07
    енка
    -0.07
     nên
    -0.06
     Atlantis
    -0.06
     Cunningham
    -0.06
    。那
    -0.06
    xac
    -0.06
    ....↵
    -0.06
    みたい
    -0.06
    POSITIVE LOGITS
    acist
    0.07
    gs
    0.06
    _med
    0.06
     FULL
    0.06
     betrayed
    0.06
    zeug
    0.06
     verb
    0.06
     znamená
    0.06
     motor
    0.06
    'h
    0.06
    Act Density 0.239%

    No Known Activations