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

    Neuronpedia

    INDEX
    Explanations

    ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chociaż
    -0.07
     <%
    -0.07
     contrasts
    -0.07
     blitz
    -0.06
    farm
    -0.06
    溪
    -0.06
     washing
    -0.06
    挣扎
    -0.06
    aar
    -0.06
     luxe
    -0.06
    POSITIVE LOGITS
    宝贵的
    0.08
     bitcoins
    0.08
     موا
    0.07
    _plugins
    0.07
    HasBeenSet
    0.07
    技术和
    0.07
     Sparse
    0.07
    CA
    0.07
    (origin
    0.07
    ENTIC
    0.07
    Act Density 0.007%

    No Known Activations