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

    Neuronpedia

    INDEX
    Explanations

    behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ph
    -0.07
    Pizza
    -0.07
    (ii
    -0.07
    _POINTER
    -0.06
     :-)
    -0.06
    :L
    -0.06
    فى
    -0.06
     ;-)
    -0.06
     huh
    -0.06
    罢了
    -0.06
    POSITIVE LOGITS
     quà
    0.08
    _pk
    0.07
     Berkeley
    0.07
    丰厚
    0.07
    languages
    0.07
    公安局
    0.07
    ปก
    0.07
     wardrobe
    0.07
    贯彻落实
    0.06
    berapa
    0.06
    Act Density 0.002%

    No Known Activations