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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     menjadi
    -0.07
     آسی
    -0.06
    _bulk
    -0.06
     влади
    -0.06
     maliyet
    -0.06
     choke
    -0.06
     bunlar
    -0.06
     者
    -0.06
     を
    -0.06
    enarios
    -0.06
    POSITIVE LOGITS
    Instrument
    0.07
     tuyên
    0.07
     notion
    0.07
     И
    0.07
    Mirror
    0.06
    であ
    0.06
    observation
    0.06
     cran
    0.06
    except
    0.06
     Ninth
    0.06
    Act Density 0.001%

    No Known Activations