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

    Neuronpedia

    INDEX
    Explanations

    say ending -e

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ETERS
    -0.06
    enums
    -0.06
     bans
    -0.06
    templ
    -0.06
    だろう
    -0.06
    :=
    -0.06
     masterpiece
    -0.06
    	y
    -0.06
     columns
    -0.06
    particle
    -0.06
    POSITIVE LOGITS
     ORIGINAL
    0.07
    ится
    0.07
     콜
    0.07
    اتف
    0.06
     �
    0.06
     sur
    0.06
     DOS
    0.06
    escal
    0.06
     абсолют
    0.06
     نظامی
    0.06
    Act Density 0.273%

    No Known Activations