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

    Neuronpedia

    INDEX
    Explanations

    lists, numbers, or ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    褶
    0.40
     থাকিত
    0.38
     રહેશે
    0.37
     memorabilia
    0.37
     विदेशों
    0.36
    लक्ष
    0.35
     রহিল
    0.35
    綃
    0.35
    бие
    0.35
    кинуло
    0.34
    POSITIVE LOGITS
     sistemas
    0.41
     동작
    0.40
     cias
    0.40
    Throttle
    0.40
    Tensor
    0.39
    Layer
    0.39
    istema
    0.38
     tienes
    0.38
     Sistemas
    0.38
    ([
    0.37
    Act Density 0.001%

    No Known Activations