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

    Neuronpedia

    INDEX
    Explanations

    atomic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    临
    -0.28
    istr
    -0.27
    éĹªçĶµ
    -0.27
    ä¼ļ计
    -0.26
    etz
    -0.25
    rais
    -0.25
    æĿ¥ä¸įåıĬ
    -0.25
    æĸ°éĹ»
    -0.25
    EA
    -0.25
    .FIELD
    -0.24
    POSITIVE LOGITS
    rox
    0.29
     Fauc
    0.27
    usher
    0.26
    |h
    0.25
     Minist
    0.25
    crow
    0.25
    {},
    0.24
     responseType
    0.23
    åıijå±ķ空éĹ´
    0.23
    testimonial
    0.23
    Act Density 0.000%

    No Known Activations