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

    Neuronpedia

    INDEX
    Explanations

    preparation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sam
    -0.07
     Sam
    -0.06
    유머
    -0.06
     dẫn
    -0.06
    \CMS
    -0.06
     podium
    -0.06
     acknowledge
    -0.06
     Nguyen
    -0.06
    라는
    -0.06
    PAY
    -0.05
    POSITIVE LOGITS
     uç
    0.07
     ман
    0.07
    ティ
    0.06
    =config
    0.06
    urvey
    0.06
     tether
    0.06
    mae
    0.06
     "()
    0.06
    크
    0.06
    option
    0.06
    Act Density 0.005%

    No Known Activations