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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ستی
    -0.07
    <Contact
    -0.07
    Extras
    -0.06
     будуть
    -0.06
    hw
    -0.06
    lol
    -0.06
     블
    -0.06
    clients
    -0.06
    道路
    -0.06
    (cos
    -0.06
    POSITIVE LOGITS
     laten
    0.07
    _ai
    0.07
     brightly
    0.06
    だと
    0.06
     featuring
    0.06
    .par
    0.06
     Finally
    0.06
    _DISABLE
    0.06
    (anchor
    0.06
     unless
    0.06
    Act Density 0.006%

    No Known Activations