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

    Neuronpedia

    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parking
    -0.08
     başlayan
    -0.07
    _CONTAINER
    -0.07
     unlawful
    -0.07
    廷
    -0.07
    ٹل
    -0.07
    Dp
    -0.07
     cemetery
    -0.07
     starter
    -0.07
     пиш
    -0.07
    POSITIVE LOGITS
     outperform
    0.10
     גבוה
    0.10
    榜
    0.09
     unbeaten
    0.09
    Recommendation
    0.09
     rankings
    0.09
     variability
    0.09
     ranking
    0.09
    Performance
    0.08
     desirable
    0.08
    Act Density 0.009%

    No Known Activations