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

    Neuronpedia

    INDEX
    Explanations

    data properties/attributes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <form
    -0.07
    辛
    -0.07
    �
    -0.06
     broker
    -0.06
     ettik
    -0.06
     multiplic
    -0.06
     Baz
    -0.06
    集中
    -0.06
     bạc
    -0.06
     اصفه
    -0.06
    POSITIVE LOGITS
     بين
    0.08
     mainAxisAlignment
    0.07
     러
    0.06
     活
    0.06
     老
    0.06
    .multiply
    0.06
     непри
    0.06
     této
    0.06
    ategory
    0.06
     additionally
    0.06
    Act Density 0.033%

    No Known Activations