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

    Neuronpedia

    INDEX
    Explanations

    adjective noun pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    注意事项
    0.74
    unicorn
    0.71
    ミュニ
    0.69
    शिक
    0.68
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.66
    NC
    0.66
    パラメータ
    0.64
     தொடங்கி
    0.64
    imbangan
    0.63
    מק
    0.63
    POSITIVE LOGITS
     Peru
    0.83
     Spain
    0.78
    Spain
    0.76
     Lea
    0.74
     hive
    0.73
     Dems
    0.72
    ětí
    0.72
     bees
    0.72
     bee
    0.71
     stars
    0.71
    Act Density 0.901%

    No Known Activations