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

    Neuronpedia

    INDEX
    Explanations

    actuarial science and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     will
    0.75
    ன்
    0.59
     thyroid
    0.55
    ное
    0.54
    стойчи
    0.54
    "
    0.54
    ной
    0.54
     presentación
    0.53
    лся
    0.52
    ："
    0.52
    POSITIVE LOGITS
     aggiungere
    0.49
     jedną
    0.49
    ၿ
    0.48
    Page
    0.48
     nằm
    0.48
    ak
    0.47
    ד
    0.47
    am
    0.46
    Year
    0.46
     поверну
    0.46
    Act Density 0.003%

    No Known Activations