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

    Neuronpedia

    INDEX
    Explanations

    your health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.68
     in
    0.62
    ram
    0.60
     matching
    0.59
    and
    0.58
     Opinions
    0.58
     about
    0.55
    '-
    0.54
     from
    0.54
     Conclusions
    0.54
    POSITIVE LOGITS
     saúde
    0.98
     невероят
    0.97
     natureza
    0.96
     Saúde
    0.93
     отправи
    0.91
     increíble
    0.90
     மேற்கு
    0.90
    Benzoimidazole
    0.89
     tío
    0.89
    âce
    0.89
    Act Density 0.010%

    No Known Activations