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

    Neuronpedia

    INDEX
    Explanations

    but followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    To
    0.42
    xx
    0.42
    obby
    0.42
    okes
    0.39
     போன்ற
    0.39
    更能
    0.39
     最新
    0.38
     To
    0.38
    bin
    0.38
    owanie
    0.38
    POSITIVE LOGITS
     också
    0.51
     tiež
    0.50
     auch
    0.48
     ايضا
    0.46
     ebenfalls
    0.45
     arī
    0.44
     też
    0.43
     still
    0.43
     ultimately
    0.43
    まだまだ
    0.43
    Act Density 0.003%

    No Known Activations