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

    Neuronpedia

    INDEX
    Explanations

    acknowledgment of importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pept
    0.43
    rš
    0.40
     ভাইকে
    0.40
    umont
    0.39
    ভাই
    0.38
     Sadie
    0.38
     WordPress
    0.38
     tuổi
    0.38
    lada
    0.38
     Mechanic
    0.38
    POSITIVE LOGITS
     prizn
    0.41
    Acknowled
    0.40
    acknowled
    0.40
     acknowledging
    0.39
    Acknowledgements
    0.39
     acknowledges
    0.38
    acknowledge
    0.38
    facing
    0.38
    acknow
    0.38
    сійскай
    0.37
    Act Density 0.000%

    No Known Activations