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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ------+
    -0.07
    到了
    -0.07
     ren
    -0.07
    ()).
    -0.07
    ाम
    -0.06
     ев
    -0.06
     далі
    -0.06
    -add
    -0.06
     зб
    -0.06
    530
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ��
    0.06
     Newsp
    0.06
    etration
    0.06
     intptr
    0.06
     itk
    0.06
    Revision
    0.06
     Servlet
    0.06
    KeyUp
    0.06
    ेबस
    0.06
    Act Density 0.089%

    No Known Activations