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

    Neuronpedia

    INDEX
    Explanations

    describes a sentence or word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Finite
    0.49
     Noetherian
    0.48
     सौंद
    0.47
     Rhine
    0.46
     τρόπο
    0.46
    ganggu
    0.45
    ground
    0.45
    finite
    0.44
     जानें
    0.44
     dàng
    0.44
    POSITIVE LOGITS
    페
    0.45
     Вам
    0.41
    дир
    0.40
     drz
    0.40
     antiguas
    0.40
    টিয়
    0.40
    ور
    0.39
    рить
    0.39
     derivations
    0.39
    你
    0.39
    Act Density 0.003%

    No Known Activations