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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    upert
    -0.08
    狩
    -0.07
     large
    -0.07
     查询
    -0.07
     quoting
    -0.07
     saja
    -0.07
    Du
    -0.07
    判处
    -0.06
    总结
    -0.06
    怎么看
    -0.06
    POSITIVE LOGITS
    ２
    0.07
    فعاليات
    0.07
     sparkling
    0.07
    Birthday
    0.07
     shuffle
    0.06
    ８
    0.06
     breat
    0.06
    -fly
    0.06
    _AB
    0.06
     Gobierno
    0.06
    Act Density 0.010%

    No Known Activations