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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不同
    -0.07
    京剧
    -0.07
    进取
    -0.07
     sup
    -0.07
    _requires
    -0.07
    风采
    -0.07
    计较
    -0.06
     למצוא
    -0.06
     boosts
    -0.06
    itten
    -0.06
    POSITIVE LOGITS
    처럼
    0.07
    ‣
    0.07
     рам
    0.07
    Glass
    0.07
    hk
    0.06
    )+"
    0.06
    otp
    0.06
    _CHUNK
    0.06
     Linked
    0.06
    ▴
    0.06
    Act Density 0.011%

    No Known Activations