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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JNI
    -0.07
    认
    -0.06
    ']↵↵
    -0.06
     Stad
    -0.06
     Rudd
    -0.06
    propri
    -0.06
     coworkers
    -0.06
     wholesalers
    -0.06
    amaz
    -0.06
    tour
    -0.06
    POSITIVE LOGITS
    (false
    0.07
    (Http
    0.07
     кри
    0.06
     copyright
    0.06
    _HIGH
    0.06
    crawl
    0.06
    프로
    0.06
     ут
    0.06
     sigh
    0.06
    했다
    0.06
    Act Density 0.064%

    No Known Activations