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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Caribbean
    -0.07
     Ernest
    -0.06
    ВС
    -0.06
     Mahmoud
    -0.06
     Label
    -0.06
     Preservation
    -0.06
     Monitoring
    -0.06
    lov
    -0.06
     Luz
    -0.06
    entials
    -0.06
    POSITIVE LOGITS
     나라
    0.06
    .Validate
    0.06
     تومان
    0.06
     hostel
    0.06
    汇
    0.06
    hind
    0.06
    킨
    0.06
    آم
    0.06
    الب
    0.06
     کاربران
    0.06
    Act Density 0.068%

    No Known Activations