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

    Neuronpedia

    INDEX
    Explanations

    military ranks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鄃
    -0.07
     Copa
    -0.07
     entren
    -0.07
    _next
    -0.07
    炀
    -0.07
     יצ
    -0.07
    集装箱
    -0.07
    魚
    -0.06
    _CTRL
    -0.06
    웍
    -0.06
    POSITIVE LOGITS
    LLLL
    0.06
     behavior
    0.06
    𝐔
    0.06
    但她
    0.06
    أسباب
    0.06
     razor
    0.06
    ikhail
    0.06
    就有
    0.06
     применения
    0.06
     Qi
    0.06
    Act Density 0.013%

    No Known Activations