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

    Neuronpedia

    INDEX
    Explanations

    water

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Player
    -0.08
     investment
    -0.07
    icho
    -0.07
    规模
    -0.07
    מעונ
    -0.06
     Kre
    -0.06
    année
    -0.06
    治愈
    -0.06
    dy
    -0.06
     登
    -0.06
    POSITIVE LOGITS
    getSimpleName
    0.07
     кноп
    0.07
    表扬
    0.07
    aría
    0.07
    /left
    0.07
    Һ
    0.07
    �
    0.07
    宁愿
    0.07
    习惯
    0.07
    手機
    0.06
    Act Density 0.005%

    No Known Activations