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

    Neuronpedia

    INDEX
    Explanations

    stress relief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unsupported
    0.68
     حدا
    0.68
    দ্ব
    0.67
     Inte
    0.67
     integrale
    0.67
     четы
    0.66
     foreach
    0.66
    原生
    0.66
     maksimum
    0.66
     Тыва
    0.66
    POSITIVE LOGITS
     easing
    2.01
     calmed
    2.01
     alleviate
    2.00
     soothe
    1.90
     calming
    1.89
     eased
    1.88
     alleviating
    1.85
     soothing
    1.81
     alleviated
    1.81
     eases
    1.79
    Act Density 0.606%

    No Known Activations