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

    Neuronpedia

    INDEX
    Explanations

    diseases, disabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    系
    -0.07
     si
    -0.07
    亶
    -0.07
    joined
    -0.07
    你需要
    -0.07
    즁
    -0.06
     whisk
    -0.06
    neider
    -0.06
     государственн
    -0.06
     tensor
    -0.06
    POSITIVE LOGITS
     Oscars
    0.07
     lifted
    0.07
     Lar
    0.07
    -la
    0.07
    ">
    0.07
    سؤال
    0.06
    몯
    0.06
     Arena
    0.06
     tran
    0.06
    almö
    0.06
    Act Density 0.021%

    No Known Activations