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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esture
    -0.07
    ofs
    -0.06
     yêu
    -0.06
     chapel
    -0.06
     ona
    -0.06
     چند
    -0.06
     Ellison
    -0.06
    -side
    -0.06
     GW
    -0.06
     Amelia
    -0.06
    POSITIVE LOGITS
     subsidiaries
    0.07
     flow
    0.07
     прор
    0.07
     flows
    0.07
     очевид
    0.06
     Nass
    0.06
     Dodd
    0.06
     зер
    0.06
    etyl
    0.06
     automáticamente
    0.06
    Act Density 0.056%

    No Known Activations