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

    Neuronpedia

    INDEX
    Explanations

    non-english languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ={['
    -0.08
    Publisher
    -0.06
     dug
    -0.06
     ammunition
    -0.06
     civ
    -0.06
     grandchildren
    -0.06
    jie
    -0.06
     contrace
    -0.06
    یا
    -0.06
    _square
    -0.06
    POSITIVE LOGITS
     ảnh
    0.07
     impacts
    0.07
     Foo
    0.07
     impacted
    0.07
     moderately
    0.07
     nějaký
    0.06
     significa
    0.06
     окт
    0.06
     prostě
    0.06
     indicator
    0.06
    Act Density 0.023%

    No Known Activations