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

    Neuronpedia

    INDEX
    Explanations

    Hotel brands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (diff
    -0.07
     attackers
    -0.06
     Diff
    -0.06
    offers
    -0.06
    Indexes
    -0.06
    —including
    -0.06
     Hamp
    -0.06
    ثمان
    -0.06
     worn
    -0.06
    _tuples
    -0.06
    POSITIVE LOGITS
    (private
    0.07
    รณ
    0.07
     pesquisa
    0.06
    .MSG
    0.06
    جوی
    0.06
     رئ
    0.06
    ující
    0.06
     misery
    0.06
    eper
    0.06
     enviado
    0.06
    Act Density 0.161%

    No Known Activations