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

    Neuronpedia

    INDEX
    Explanations

    defines or describes kinds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     λόγω
    0.30
     estava
    0.30
     क्योंकि
    0.30
     อย่า
    0.30
     будущем
    0.29
     rapaz
    0.29
     puisque
    0.29
     pourront
    0.28
     Jangan
    0.28
     yli
    0.28
    POSITIVE LOGITS
    と呼ばれる
    0.49
     defined
    0.42
    一种
    0.42
    是一种
    0.42
     refers
    0.41
     describes
    0.40
    Describes
    0.39
    An
    0.36
     термин
    0.35
    defined
    0.34
    Act Density 0.939%

    No Known Activations