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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DS
    -0.07
    attrs
    -0.07
    質量
    -0.07
    (TAG
    -0.07
    @SpringBootTest
    -0.07
    rieve
    -0.06
     Lev
    -0.06
    ROS
    -0.06
    isin
    -0.06
    何时
    -0.06
    POSITIVE LOGITS
     regarded
    0.07
     dünya
    0.07
     Sexual
    0.07
     знак
    0.07
    caracter
    0.07
    ：↵↵
    0.06
    查封
    0.06
     dragon
    0.06
     schematic
    0.06
     Clarence
    0.06
    Act Density 0.072%

    No Known Activations