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

    Neuronpedia

    INDEX
    Explanations

    finance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :hidden
    -0.08
    umlah
    -0.07
    Mur
    -0.07
    림
    -0.06
     метал
    -0.06
     컴
    -0.06
    çiler
    -0.06
     omp
    -0.06
    ัง
    -0.06
     Dunk
    -0.06
    POSITIVE LOGITS
    uddle
    0.08
    manent
    0.07
     REQUEST
    0.07
    /Test
    0.07
     illegal
    0.06
    ».↵
    0.06
    kup
    0.06
    TestMethod
    0.06
    getc
    0.06
    /'↵
    0.06
    Act Density 0.003%

    No Known Activations