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

    Neuronpedia

    INDEX
    Explanations

    name __

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पटक
    0.67
     कृपया
    0.66
     अल
    0.65
    Here
    0.62
     listed
    0.62
     here
    0.62
     प्रथ
    0.62
     yr
    0.60
    ये
    0.60
    単
    0.60
    POSITIVE LOGITS
    arses
    0.95
    0.90
     sorprendente
    0.88
     cárcel
    0.84
    irse
    0.81
    мец
    0.80
     وذلك
    0.80
    ｓ
    0.80
     సమయంలో
    0.80
     বিষয়টা
    0.79
    Act Density 0.047%

    No Known Activations