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

    Neuronpedia

    INDEX
    Explanations

    parks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    技能培训
    -0.08
    保證
    -0.07
    保安
    -0.07
    _NUM
    -0.07
    妨碍
    -0.07
    SUM
    -0.07
    Pref
    -0.07
    _FORMAT
    -0.07
    行业发展
    -0.07
    admins
    -0.07
    POSITIVE LOGITS
    .Wait
    0.08
     Wak
    0.07
     ctr
    0.07
    飏
    0.07
     ???
    0.07
     lấy
    0.07
    vik
    0.07
     Yong
    0.07
     וכ
    0.07
    inati
    0.06
    Act Density 0.055%

    No Known Activations