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

    Neuronpedia

    INDEX
    Explanations

    fossil fuels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ill
    0.80
    the
    0.75
    ра
    0.72
    ｅ
    0.70
    。[
    0.69
    ere
    0.68
    ها
    0.68
    etas
    0.68
    told
    0.66
    。「
    0.64
    POSITIVE LOGITS
    م
    0.97
    ى
    0.97
    м
    0.84
    ↵↵
    0.81
    ’)
    0.81
     الأ
    0.79
     uygulama
    0.77
     fossil
    0.77
     كتابه
    0.75
    */
    0.74
    Act Density 0.001%

    No Known Activations