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

    Neuronpedia

    INDEX
    Explanations

    database relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parliamentary
    -0.07
     PROT
    -0.07
     national
    -0.06
    .Date
    -0.06
    description
    -0.06
    commerce
    -0.06
    stars
    -0.06
    STAT
    -0.06
    .pagination
    -0.06
    тик
    -0.06
    POSITIVE LOGITS
     처
    0.07
     Tribunal
    0.06
    ва
    0.06
     ""));↵
    0.06
     lỗi
    0.06
     사무
    0.06
     لكل
    0.06
    etler
    0.06
     ))}↵
    0.06
    خته
    0.06
    Act Density 0.017%

    No Known Activations