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

    Neuronpedia

    INDEX
    Explanations

    Recommendations and quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    自然资源
    -0.08
    Ken
    -0.07
     necessário
    -0.07
    _gen
    -0.07
     traded
    -0.07
     criminal
    -0.07
    建筑业
    -0.07
    משפחת
    -0.07
     %[
    -0.07
    Party
    -0.07
    POSITIVE LOGITS
     вз
    0.07
    bug
    0.07
    losures
    0.07
     Hơn
    0.07
     Yö
    0.07
    电话
    0.07
    咙
    0.06
    尺度
    0.06
     fost
    0.06
    샌
    0.06
    Act Density 0.115%

    No Known Activations