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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    配有
    -0.08
     climbed
    -0.07
     Можно
    -0.07
     Чтобы
    -0.07
    战斗
    -0.07
    签署了
    -0.07
     resisted
    -0.07
    โฆ
    -0.07
    letic
    -0.06
     yardım
    -0.06
    POSITIVE LOGITS
    近代
    0.07
     Lowe
    0.07
    REAK
    0.07
     doom
    0.07
     sway
    0.07
    pery
    0.07
     treff
    0.07
     recession
    0.07
    üß
    0.07
    古今
    0.07
    Act Density 0.002%

    No Known Activations