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

    Neuronpedia

    INDEX
    Explanations

    FastAPI and Pydantic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unpleasant
    0.39
     उपन्यास
    0.39
     disagreeable
    0.39
     pleasures
    0.38
    PLAIN
    0.38
     philanthropic
    0.37
    ጇ
    0.36
    Ple
    0.36
    ент
    0.35
    臨界
    0.35
    POSITIVE LOGITS
     помещение
    0.43
    ronaut
    0.40
     Лю
    0.38
    ருக
    0.38
    라우
    0.38
    माने
    0.37
     помещения
    0.37
     handleClick
    0.37
    eyse
    0.37
     वाहनों
    0.36
    Act Density 0.000%

    No Known Activations