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

    Neuronpedia

    INDEX
    Explanations

    products posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -operation
    -0.08
     baby
    -0.07
    Travel
    -0.07
    -China
    -0.07
     Kỳ
    -0.07
    Contracts
    -0.07
    (bytes
    -0.06
    冬
    -0.06
    -btn
    -0.06
     Share
    -0.06
    POSITIVE LOGITS
     בנוסף
    0.07
    ogens
    0.07
     sailors
    0.07
    התנגד
    0.07
    graphic
    0.07
     Hok
    0.07
     Packers
    0.06
     언제
    0.06
     Disable
    0.06
     timeless
    0.06
    Act Density 0.104%

    No Known Activations