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

    Neuronpedia

    INDEX
    Explanations

    however, although, though

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     como
    0.46
     inclusiv
    0.44
     sifatida
    0.42
     institucional
    0.42
     direito
    0.41
     aici
    0.41
     oficialmente
    0.41
    សម្រាប់ការ
    0.39
     exactamente
    0.39
     continuidad
    0.38
    POSITIVE LOGITS
    though
    0.49
    although
    0.49
    However
    0.46
     சிந்த
    0.46
     However
    0.45
     tetapi
    0.45
     لیکن
    0.43
     그러나
    0.42
     Tuttavia
    0.42
    虽然
    0.42
    Act Density 0.002%

    No Known Activations