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

    Neuronpedia

    INDEX
    Explanations

    scientific study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ہد
    0.45
     convincing
    0.45
     giveaway
    0.43
     विकल्प
    0.42
     విని
    0.42
    亮点
    0.42
    MsgCallBack
    0.42
     ලබා
    0.41
     উপস্থিত
    0.41
    डिएट
    0.40
    POSITIVE LOGITS
     studying
    2.11
     study
    2.00
     изучение
    1.91
     Studying
    1.88
     изучения
    1.88
     studies
    1.83
     estudo
    1.80
     estudar
    1.80
     изуча
    1.78
     अध्ययन
    1.77
    Act Density 0.020%

    No Known Activations