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

    Neuronpedia

    INDEX
    Explanations

    Publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Blend
    -0.07
    工程
    -0.06
     Stations
    -0.06
     vil
    -0.06
    	struct
    -0.06
    Якщо
    -0.06
     iod
    -0.06
    ені
    -0.06
    이라는
    -0.06
    Tile
    -0.06
    POSITIVE LOGITS
    urge
    0.06
    _sentences
    0.06
     Ala
    0.06
     GK
    0.06
    eksiyon
    0.06
    ยนตร
    0.06
    /save
    0.06
     setuptools
    0.06
     blacks
    0.06
    zel
    0.06
    Act Density 0.035%

    No Known Activations