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

    Neuronpedia

    INDEX
    Explanations

    정

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EMALE
    -0.07
    갖
    -0.07
    .glide
    -0.07
    厣
    -0.07
     endurance
    -0.06
     уника
    -0.06
     sıcak
    -0.06
    Fade
    -0.06
    راه
    -0.06
    (routes
    -0.06
    POSITIVE LOGITS
     정
    0.08
    正
    0.08
    重
    0.07
    정
    0.07
    最終
    0.07
     Ding
    0.06
    alignment
    0.06
    "W
    0.06
    (orig
    0.06
     UNS
    0.06
    Act Density 0.011%

    No Known Activations