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

    Neuronpedia

    INDEX
    Explanations

    people and relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ابه
    -0.06
    街道
    -0.06
    ,SLOT
    -0.06
    吧
    -0.06
    zar
    -0.06
    \Factories
    -0.06
    قى
    -0.06
    군요
    -0.06
    Lets
    -0.06
    ornment
    -0.06
    POSITIVE LOGITS
     Valle
    0.08
    published
    0.07
     관
    0.06
     Nursing
    0.06
     ince
    0.06
     sincerely
    0.06
     berry
    0.06
     metrics
    0.06
     Hitch
    0.06
     pueden
    0.06
    Act Density 0.001%

    No Known Activations