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

    Neuronpedia

    INDEX
    Explanations

    Inequalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نبود
    -0.08
     conduct
    -0.07
     deeds
    -0.07
     Be
    -0.07
    оке
    -0.07
     Conduct
    -0.07
     R
    -0.07
     Bar
    -0.07
     د
    -0.07
    Improved
    -0.06
    POSITIVE LOGITS
    .month
    0.06
    液
    0.06
    _FULL
    0.06
     дослідження
    0.06
    -height
    0.06
     输
    0.06
    Detalle
    0.06
     QName
    0.05
    ágenes
    0.05
     startTime
    0.05
    Act Density 0.023%

    No Known Activations