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

    Neuronpedia

    INDEX
    Explanations

    roi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     summ
    -0.07
     tended
    -0.07
    수
    -0.07
    patch
    -0.07
     VER
    -0.07
    eme
    -0.07
    錯誤
    -0.07
     Product
    -0.07
    灌
    -0.06
    运维
    -0.06
    POSITIVE LOGITS
     الحوثي
    0.07
    .iloc
    0.07
     Graham
    0.07
    ―
    0.07
    ʟ
    0.07
    Triangles
    0.07
    _ac
    0.07
     الخليج
    0.07
    _roi
    0.07
    엮
    0.06
    Act Density 0.002%

    No Known Activations