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

    Neuronpedia

    INDEX
    Explanations

    regular exercise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     позволя
    0.80
     тре
    0.79
    рун
    0.78
    oren
    0.77
    erre
    0.76
    दुर्
    0.70
     су
    0.70
     тер
    0.70
    旻
    0.70
    )',
    0.68
    POSITIVE LOGITS
     embodiments
    0.81
     covariant
    0.75
    Enfin
    0.73
    ‌هایی
    0.73
     subscripts
    0.71
     filaments
    0.71
     potentialities
    0.70
     PayPay
    0.70
    ский
    0.70
    ှ
    0.70
    Act Density 0.000%

    No Known Activations