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

    Neuronpedia

    INDEX
    Explanations

    uncountable nouns and subject-verb agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ەد
    0.39
    ابقات
    0.36
    âne
    0.36
    رمان
    0.36
    რება
    0.34
    ቻል
    0.34
    ುತ್ತವೆ
    0.34
    ющей
    0.34
     auction
    0.33
    ಬಹುದು
    0.33
    POSITIVE LOGITS
    0.64
    #######
    0.56
    0.56
    琀
    0.48
    昀
    0.48
    0.48
    0.44
     Lecture
    0.44
    0.44
    ฀
    0.44
    Act Density 0.002%

    No Known Activations