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

    Neuronpedia

    INDEX
    Explanations

    say "th" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wingConstants
    -0.08
     或
    -0.06
    шей
    -0.06
     paragraphs
    -0.06
    ALSE
    -0.06
    ยน
    -0.06
     Họ
    -0.06
    <S
    -0.06
    .isTrue
    -0.06
    ponses
    -0.06
    POSITIVE LOGITS
     заболеваний
    0.07
    ,''
    0.07
    amaz
    0.07
    umm
    0.06
     однов
    0.06
    stag
    0.06
     gritty
    0.06
    あった
    0.06
    atories
    0.06
     ties
    0.06
    Act Density 0.018%

    No Known Activations