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

    Neuronpedia

    INDEX
    Explanations

    million

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    av
    -0.07
     adult
    -0.07
     FRIEND
    -0.07
    الی
    -0.07
    塞
    -0.07
    (address
    -0.07
    结果
    -0.06
    band
    -0.06
     sebuah
    -0.06
     experience
    -0.06
    POSITIVE LOGITS
    ?>
↵
    0.06
    /")
    0.06
    .");
↵
    0.06
    -notification
    0.06
     tối
    0.06
    ...
↵
    0.06
     Durant
    0.06
    作为
    0.05
    /gin
    0.05
    "]
↵
    0.05
    Act Density 0.018%

    No Known Activations