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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diminish
    -0.07
     [])
    -0.07
     interval
    -0.07
    信号
    -0.07
    Ped
    -0.07
     Stream
    -0.07
     ()
    -0.06
    irim
    -0.06
    UserID
    -0.06
     Markus
    -0.06
    POSITIVE LOGITS
    合作关系
    0.07
    恝
    0.07
     reunion
    0.07
     didReceiveMemoryWarning
    0.06
    نامج
    0.06
    cooked
    0.06
    dsa
    0.06
    смотр
    0.06
    ђ
    0.06
    физическ
    0.06
    Act Density 0.045%

    No Known Activations