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

    Neuronpedia

    INDEX
    Explanations

    oxidative stress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     underlies
    0.53
     workloads
    0.51
     аутох
    0.49
     commandBuffer
    0.48
    एगी
    0.47
    ayı
    0.47
     storms
    0.46
     списка
    0.46
     সংখ
    0.46
    颼
    0.46
    POSITIVE LOGITS
    न
    0.54
    نا
    0.51
    ྛ
    0.51
    ۰
    0.50
    لا
    0.49
    سی
    0.49
    я
    0.49
    นด์
    0.49
    نی
    0.48
    نیا
    0.48
    Act Density 0.000%

    No Known Activations