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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Real
    -0.07
    ouv
    -0.06
     REAL
    -0.06
     renowned
    -0.06
     flavour
    -0.06
    STS
    -0.06
     Clay
    -0.06
    Amazing
    -0.06
    fifo
    -0.06
    Pure
    -0.06
    POSITIVE LOGITS
    )의
    0.07
     자신
    0.07
    ằm
    0.07
     مبت
    0.07
     �
    0.07
     �
    0.07
     آزمایش
    0.07
    uctor
    0.07
     همسر
    0.06
    \Admin
    0.06
    Act Density 0.080%

    No Known Activations