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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /on
    -0.06
     заклад
    -0.06
    Entities
    -0.06
    igmoid
    -0.06
    保護
    -0.06
     Va
    -0.06
    esome
    -0.06
     eski
    -0.06
    almart
    -0.05
    alue
    -0.05
    POSITIVE LOGITS
    τι
    0.06
                       ↵
    0.06
    ">--}}↵
    0.06
     xuất
    0.06
    )'↵
    0.06
    QUENCY
    0.06
     BYU
    0.06
    ?>"↵
    0.06
     ac
    0.06
     >
↵
    0.06
    Act Density 0.008%

    No Known Activations