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

    Neuronpedia

    INDEX
    Explanations

    database roles and users

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Suppose
    0.94
     PTA
    0.91
    ‌های
    0.90
     మంది
    0.89
    Suppose
    0.87
     দিকে
    0.86
     зна
    0.84
     cmap
    0.84
    的代码
    0.83
    sthe
    0.83
    POSITIVE LOGITS
    tj
    0.82
    sj
    0.79
    ς
    0.79
     ۽
    0.76
     alebo
    0.75
     proclaimed
    0.75
     बृ
    0.74
    ঙ্গ
    0.74
     جوړونکي
    0.74
    َّا
    0.73
    Act Density 0.200%

    No Known Activations