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

    Neuronpedia

    INDEX
    Explanations

    first things first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بشكل
    0.89
     மாதிர
    0.84
    方法的
    0.79
    들의
    0.78
    就行
    0.76
     부분이
    0.76
     طريقة
    0.74
    नाच्या
    0.74
     방법을
    0.73
    నాల
    0.73
    POSITIVE LOGITS
     dran
    0.77
    ächlich
    0.77
    েষে
    0.76
    awarkan
    0.76
     nhiên
    0.74
     freep
    0.72
    ಂತೆ
    0.72
     xwe
    0.72
     देम
    0.72
    ienie
    0.72
    Act Density 0.044%

    No Known Activations