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

    Neuronpedia

    INDEX
    Explanations

    quantifiers such as all, each, every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    现象
    0.41
    长大
    0.41
     შორის
    0.40
    众
    0.40
    لار
    0.39
     pracovní
    0.39
    物体
    0.38
    有所
    0.38
    道府県
    0.38
    ্ত
    0.38
    POSITIVE LOGITS
    =[
    0.44
    &\
    0.44
     ക
    0.43
    MQTT
    0.43
     lemon
    0.41
    CTED
    0.41
     रे
    0.41
    CDF
    0.41
     キ
    0.40
    SR
    0.40
    Act Density 0.011%

    No Known Activations