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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns/adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¸ī个æĸ¹éĿ¢
    -0.25
    existent
    -0.25
    hell
    -0.25
    æĬĢæľ¯æ°´å¹³
    -0.24
    è¿Ļéĥ¨åĪĨ
    -0.24
    è¿Ļä¸ī个
    -0.24
    è¿IJéĢģ
    -0.24
    ump
    -0.23
    åİħ
    -0.23
    éĹ´éļĻ
    -0.23
    POSITIVE LOGITS
    |$
    0.27
    |M
    0.26
    å°±å¼Ģå§ĭ
    0.25
    \"";↵
    0.24
     Aqu
    0.24
     Trou
    0.24
     journalists
    0.24
    ละ
    0.24
    енно
    0.24
    æĸ¹æ³ķ
    0.23
    Act Density 0.004%

    No Known Activations