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

    Neuronpedia

    INDEX
    Explanations

    in context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essi
    0.45
     მათი
    0.44
    ™.
    0.44
     озна
    0.42
    ®.
    0.41
     шля
    0.41
     largos
    0.40
    nytimes
    0.40
    istor
    0.40
     उनका
    0.39
    POSITIVE LOGITS
    出现在
    0.80
    នៅក្នុង
    0.79
     trong
    0.74
     katika
    0.73
     لە
    0.71
     ở
    0.70
     during
    0.68
     فى
    0.67
     στην
    0.67
    ใน
    0.66
    Act Density 1.129%

    No Known Activations