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

    Neuronpedia

    INDEX
    Explanations

    ued

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    علاج
    -0.08
     <!--
    -0.07
    接管
    -0.07
    马丁
    -0.07
    舜
    -0.06
    清理
    -0.06
     John
    -0.06
     giữa
    -0.06
    瑧
    -0.06
    integr
    -0.06
    POSITIVE LOGITS
    .Reverse
    0.07
     Mandatory
    0.07
     없습니다
    0.07
    _place
    0.07
     pylab
    0.06
    이라
    0.06
     로
    0.06
    一个星期
    0.06
     prec
    0.06
     Assembly
    0.06
    Act Density 0.000%

    No Known Activations