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

    Neuronpedia

    INDEX
    Explanations

    due to / caused by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зайн
    0.79
    aglia
    0.77
    <unused324>
    0.74
    <unused400>
    0.74
     desempeño
    0.72
    <unused2014>
    0.71
    Escolh
    0.71
    mathscr
    0.71
     подробно
    0.70
    рил
    0.70
    POSITIVE LOGITS
     due
    3.61
    due
    3.08
     akibat
    3.01
     Due
    2.89
    Due
    2.85
     بسبب
    2.84
     caused
    2.76
     вследствие
    2.75
     devido
    2.64
     DUE
    2.62
    Act Density 0.247%

    No Known Activations