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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    עצב
    -0.07
     wereld
    -0.07
    тен
    -0.07
    (upload
    -0.07
    洹
    -0.06
    .shiro
    -0.06
    不尽
    -0.06
    >.</
    -0.06
    orderby
    -0.06
    ȓ
    -0.06
    POSITIVE LOGITS
    [M
    0.07
    ሲ
    0.07
    שאל
    0.06
     {:?}",
    0.06
    ////↵
    0.06
    扩展
    0.06
    Selective
    0.06
     `$
    0.06
     компании
    0.06
    <-
    0.06
    Act Density 0.112%

    No Known Activations