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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     help
    -0.60
     ujednoznacz
    -0.59
    Begriffsklä
    -0.57
    oidal
    -0.52
    slf
    -0.52
     prayer
    -0.50
    ooker
    -0.49
    rhosis
    -0.49
    RectangleBorder
    -0.49
    ngilizce
    -0.49
    POSITIVE LOGITS
     stället
    0.62
     mérite
    0.60
     Paglinawan
    0.59
     læng
    0.56
     conquête
    0.54
    Personensuche
    0.53
     mérit
    0.52
     médec
    0.52
     Efq
    0.52
     Jefus
    0.51
    Act Density 0.001%

    No Known Activations