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

    Neuronpedia

    INDEX
    Explanations

    hydration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    严谨
    -0.07
    	vo
    -0.07
    isActive
    -0.07
     xPos
    -0.07
    擂
    -0.07
    .acc
    -0.07
    Ⓡ
    -0.07
     Мак
    -0.07
    ォ
    -0.07
    GameState
    -0.06
    POSITIVE LOGITS
     хочет
    0.08
    �
    0.07
     dehydration
    0.07
    润滑
    0.07
    重要な
    0.07
    iga
    0.07
    うちに
    0.07
    ა
    0.07
     generators
    0.07
     וש
    0.07
    Act Density 0.003%

    No Known Activations