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

    Neuronpedia

    INDEX
    Explanations

    manner of operation or execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    řízení
    0.83
    тесь
    0.79
     الرسمي
    0.79
    rylic
    0.78
     வெளி
    0.75
     jednoduch
    0.75
    ření
    0.74
    自然的
    0.74
    ম্বে
    0.73
    鲞
    0.72
    POSITIVE LOGITS
    នូវ
    1.13
     without
    1.01
     from
    0.95
     through
    0.94
    ៗ
    0.91
     rather
    0.89
     melalui
    0.88
     via
    0.88
     during
    0.87
    पणे
    0.85
    Act Density 0.128%

    No Known Activations