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

    Neuronpedia

    INDEX
    Explanations

    code and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    δό
    -0.06
     Radius
    -0.06
    .Grid
    -0.06
     parliamentary
    -0.06
    ARING
    -0.06
     Parliamentary
    -0.06
    ネル
    -0.06
    aring
    -0.06
    ủy
    -0.06
     erhalten
    -0.06
    POSITIVE LOGITS
    	So
    0.08
     aio
    0.07
     WARRANTY
    0.06
    ●
    0.06
    _excel
    0.06
     Tomas
    0.06
     assert
    0.06
     dancer
    0.06
    洛
    0.06
    :length
    0.06
    Act Density 0.033%

    No Known Activations