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

    Neuronpedia

    INDEX
    Explanations

    strategy or order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Medical
    0.49
     Medical
    0.47
     의료
    0.45
     کرسک
    0.44
     medical
    0.43
     biomedical
    0.41
     मेडिकल
    0.40
    医疗
    0.40
    Healthcare
    0.39
     фармацев
    0.39
    POSITIVE LOGITS
    ждает
    0.45
     stratégie
    0.42
     strategy
    0.41
    കേന്ദ്രം
    0.40
    並沒有
    0.40
    ňuje
    0.40
    strategy
    0.39
    篩
    0.39
     strategia
    0.39
     representing
    0.39
    Act Density 0.003%

    No Known Activations