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

    Neuronpedia

    INDEX
    Explanations

    responsible for damages or losses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மருத்துவ
    0.82
     medical
    0.77
     medizin
    0.75
     medically
    0.74
     poważ
    0.71
     deserves
    0.71
     Medical
    0.71
     desperately
    0.70
    ငံ
    0.69
     clinically
    0.68
    POSITIVE LOGITS
     arising
    1.02
     losses
    0.97
     возника
    0.95
     mishaps
    0.94
    損失
    0.93
     accidents
    0.89
    losses
    0.88
     misuse
    0.87
     daños
    0.87
     mishap
    0.86
    Act Density 0.014%

    No Known Activations