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

    Neuronpedia

    INDEX
    Explanations

    dropdown lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (index
    -0.07
     habitats
    -0.07
     assisted
    -0.07
     famed
    -0.07
     Hakk
    -0.06
     zpět
    -0.06
    eil
    -0.06
     shelter
    -0.06
     discussed
    -0.06
    minster
    -0.06
    POSITIVE LOGITS
    RCT
    0.06
     hearty
    0.06
    �始化
    0.06
     بنابراین
    0.06
     fla
    0.06
     wallpaper
    0.06
    ｿ
    0.06
    �
    0.06
     propTypes
    0.06
    CppType
    0.06
    Act Density 0.010%

    No Known Activations