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

    Neuronpedia

    INDEX
    Explanations

    pecans or INT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ży
    0.78
     tutta
    0.75
     prête
    0.74
     riesce
    0.72
     yang
    0.72
     especie
    0.71
     toute
    0.71
    ைகளின்
    0.70
     espécie
    0.70
    效
    0.70
    POSITIVE LOGITS
    Л
    0.81
     receptions
    0.78
     fewest
    0.76
     ア
    0.75
    別途
    0.74
    兒童
    0.72
     ヘ
    0.72
     lollipop
    0.71
     ロ
    0.70
     Aufmerksamkeit
    0.70
    Act Density 0.992%

    No Known Activations