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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Us
    -0.07
    "}
    -0.07
    ᗩ
    -0.07
     ליד
    -0.07
    _MAXIMUM
    -0.07
     Lý
    -0.07
     physicist
    -0.07
     myth
    -0.07
    厅
    -0.06
    狐
    -0.06
    POSITIVE LOGITS
     Connie
    0.07
    不断
    0.07
    FML
    0.07
    capitalize
    0.06
    鲜
    0.06
    🍴
    0.06
     dac
    0.06
    �
    0.06
     Countdown
    0.06
    cae
    0.06
    Act Density 0.051%

    No Known Activations