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

    Neuronpedia

    INDEX
    Explanations

    code imports and includes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¸įå°½
    -0.26
    ate
    -0.26
    åIJĦèĩª
    -0.25
    åĪĨåĪ«
    -0.25
    fel
    -0.25
    amin
    -0.24
    æĪĸå°Ĩ
    -0.24
    .ordinal
    -0.24
    orsch
    -0.24
    min
    -0.24
    POSITIVE LOGITS
    eturn
    0.28
    rops
    0.26
    embro
    0.26
    åĵģæł¼
    0.25
     Goods
    0.25
     retal
    0.25
    nels
    0.24
    ewood
    0.24
    è²Į
    0.24
    bsd
    0.23
    Act Density 0.019%

    No Known Activations