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

    Neuronpedia

    INDEX
    Explanations

    grammar and tenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    胖
    -0.08
     Unexpected
    -0.07
    亏损
    -0.07
     weighs
    -0.07
    出汗
    -0.07
    这篇
    -0.07
    ifr
    -0.07
     Childhood
    -0.07
     weigh
    -0.07
    增长
    -0.06
    POSITIVE LOGITS
     직
    0.07
     rites
    0.07
    -na
    0.07
     obra
    0.07
     TAKE
    0.07
     ao
    0.07
     rights
    0.06
    專業
    0.06
    Chicago
    0.06
    /shared
    0.06
    Act Density 0.009%

    No Known Activations