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

    Neuronpedia

    INDEX
    Explanations

    big

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ected
    -0.08
    PW
    -0.08
    fetch
    -0.07
     connected
    -0.07
     selection
    -0.07
    RG
    -0.07
    Address
    -0.07
    功率
    -0.07
     liability
    -0.07
     масло
    -0.07
    POSITIVE LOGITS
    俗称
    0.08
    🔛
    0.07
    :before
    0.07
    睛
    0.07
    ,,,,
    0.07
     OBS
    0.07
     billboard
    0.07
     예
    0.07
    岁月
    0.07
     outdoors
    0.07
    Act Density 0.028%

    No Known Activations