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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生产经营
    -0.08
    扶贫
    -0.08
     Component
    -0.07
    Component
    -0.07
     highway
    -0.07
     merely
    -0.07
    rename
    -0.07
     Corpor
    -0.07
    EntryPoint
    -0.07
     engr
    -0.07
    POSITIVE LOGITS
    Ң
    0.08
    ₀
    0.07
     reflects
    0.07
    𝕝
    0.07
    _byte
    0.06
    发现了
    0.06
    _and
    0.06
    輝
    0.06
    첩
    0.06
    很漂亮
    0.06
    Act Density 0.019%

    No Known Activations