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

    Neuronpedia

    INDEX
    Explanations

    Inside

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offended
    -0.08
     suffering
    -0.07
    ена
    -0.07
    !\
    -0.07
    .&
    -0.07
    mr
    -0.07
    工程
    -0.07
    appen
    -0.06
    赶上
    -0.06
     det
    -0.06
    POSITIVE LOGITS
    <b
    0.07
    бир
    0.07
    sku
    0.07
    /items
    0.07
    .cam
    0.07
    /antlr
    0.07
    książ
    0.07
    ersistence
    0.07
     ARCH
    0.06
     anecd
    0.06
    Act Density 0.534%

    No Known Activations