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

    Neuronpedia

    INDEX
    Explanations

    quotation marks/parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    щего
    -0.07
    withdraw
    -0.06
    таки
    -0.06
    sı
    -0.06
     hâlâ
    -0.06
    atholic
    -0.06
     meg
    -0.06
     sprung
    -0.06
    som
    -0.06
    POSITIVE LOGITS
    arna
    0.07
     příjem
    0.07
     convey
    0.07
     matlab
    0.06
     Gill
    0.06
    :f
    0.06
     USDA
    0.06
     unwind
    0.06
    .'<
    0.06
    福
    0.06
    Act Density 0.012%

    No Known Activations