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

    Neuronpedia

    INDEX
    Explanations

    score

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SystemService
    -0.07
    _hresult
    -0.07
    _employee
    -0.07
    ocoder
    -0.06
    [vi
    -0.06
    енд
    -0.06
    UBLISH
    -0.06
     jedné
    -0.06
    '=
    -0.06
    ерів
    -0.06
    POSITIVE LOGITS
     nutritional
    0.07
     withdrawals
    0.06
    욱
    0.06
    Fitness
    0.06
     Killing
    0.06
     Apprentice
    0.06
     kir
    0.06
     celebration
    0.06
    (dx
    0.06
     Ao
    0.05
    Act Density 0.019%

    No Known Activations