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

    Neuronpedia

    INDEX
    Explanations

    Elixyr Babaghanug Fish honours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     THOMAS
    0.46
     दृष्ट
    0.40
     トー
    0.40
    limit
    0.39
    кр
    0.38
     মস্তি
    0.37
    рик
    0.37
     уничто
    0.36
    <unused492>
    0.36
    pcl
    0.36
    POSITIVE LOGITS
    Ming
    0.44
    meros
    0.41
    Mark
    0.41
    泼
    0.40
    Maria
    0.39
    Sak
    0.39
    Sh
    0.39
    ResourceManager
    0.39
    ૂ
    0.38
     resources
    0.38
    Act Density 0.000%

    No Known Activations