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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elderly
    -0.07
     stated
    -0.07
    ERS
    -0.06
    تى
    -0.06
    irtual
    -0.06
     اکتبر
    -0.06
    Cars
    -0.06
    ouser
    -0.06
    DDL
    -0.06
    -dess
    -0.06
    POSITIVE LOGITS
    /met
    0.07
     Epidemi
    0.06
    (...)
    0.06
    Добав
    0.06
    очный
    0.06
     وصلات
    0.06
    Insert
    0.06
     하면
    0.06
     unsubscribe
    0.06
     Samp
    0.06
    Act Density 0.005%

    No Known Activations