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

    Neuronpedia

    INDEX
    Explanations

    asking you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diminue
    0.56
    \
    0.54
     تَ
    0.48
     ใน
    0.46
     poprzez
    0.46
    ใน
    0.45
     oftentimes
    0.45
    攵
    0.44
     në
    0.43
    នៅក្នុង
    0.43
    POSITIVE LOGITS
     उत्सुक
    0.55
    欢迎
    0.50
     mesti
    0.49
     आवश्यक
    0.47
     préalable
    0.44
     mutlaka
    0.43
     eagerly
    0.43
     cần
    0.43
     embarrassed
    0.43
     Öffentlichkeit
    0.43
    Act Density 0.000%

    No Known Activations