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

    Neuronpedia

    INDEX
    Explanations

    prime numbers code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     key
    -0.08
     ég
    -0.08
     clave
    -0.08
     ключ
    -0.07
    .key
    -0.07
    关键
    -0.07
     judging
    -0.07
    .concat
    -0.07
     criticizing
    -0.07
     lợi
    -0.07
    POSITIVE LOGITS
    寻找
    0.13
     找
    0.11
    找
    0.11
     ಹುಡು
    0.11
     ಅಭ್ಯರ್ಥ
    0.11
    Finding
    0.10
    搜尋
    0.10
     उम्मीदवार
    0.10
     तलाश
    0.10
     搜
    0.10
    Act Density 0.021%

    No Known Activations