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

    Neuronpedia

    INDEX
    Explanations

    surge in demand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pourcentage
    0.74
    पणे
    0.73
     personnage
    0.72
    ாக்கு
    0.71
    जवळ
    0.69
    的角度
    0.68
     commentaires
    0.67
    স্পতি
    0.66
     cardia
    0.66
    说
    0.65
    POSITIVE LOGITS
     Louisa
    0.91
     Lü
    0.86
    ยายน
    0.85
    डब्ल्यू
    0.80
     वहां
    0.78
     Sach
    0.76
     всей
    0.76
     Mimi
    0.76
     Sasha
    0.75
     मचा
    0.75
    Act Density 0.007%

    No Known Activations