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

    Neuronpedia

    INDEX
    Explanations

    Christmas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sut
    -0.28
    (shift
    -0.27
    nesc
    -0.27
    sar
    -0.27
     Toilet
    -0.27
    shift
    -0.27
    èIJ½ä¸ĭ
    -0.25
     nutshell
    -0.25
    _shift
    -0.25
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.25
    POSITIVE LOGITS
    usk
    0.27
     Cong
    0.27
     p
    0.27
    ettes
    0.27
     def
    0.26
    å¥ī
    0.25
    erta
    0.24
    NBC
    0.24
    ella
    0.24
    Cong
    0.24
    Act Density 0.100%

    No Known Activations