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

    Neuronpedia

    INDEX
    Explanations

    消息

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =L
    -0.07
    業務
    -0.07
     ROT
    -0.07
    ête
    -0.06
    ("/");↵
    -0.06
    ]='
    -0.06
    _episode
    -0.06
    eat
    -0.06
     věku
    -0.06
     mmap
    -0.06
    POSITIVE LOGITS
    0.06
     ویکی
    0.06
     suy
    0.06
     처리
    0.06
     vere
    0.06
     Applicants
    0.06
    PostalCodes
    0.06
     такой
    0.06
    enses
    0.05
     wxDefault
    0.05
    Act Density 0.000%

    No Known Activations