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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     обычно
    -0.09
     preferably
    -0.08
     желательно
    -0.08
     betekent
    -0.08
     например
    -0.08
     пространство
    -0.07
     (?,
    -0.07
    スペ
    -0.07
     Обычно
    -0.07
     прот
    -0.07
    POSITIVE LOGITS
    整改
    0.08
    unds
    0.08
    收益
    0.08
    ADX
    0.08
     necklaces
    0.07
    Nd
    0.07
    -chave
    0.07
     yez
    0.07
    Danny
    0.07
    待遇
    0.07
    Act Density 0.145%

    No Known Activations