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

    Neuronpedia

    INDEX
    Explanations

    mock exams, interviews, or mockups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ώστε
    0.49
     Statist
    0.41
     malzem
    0.41
     Qb
    0.41
     Kxf
    0.40
     자료
    0.40
     Dom
    0.40
    伒
    0.39
     вирі
    0.39
     Orig
    0.38
    POSITIVE LOGITS
    Mock
    0.52
    mock
    0.44
     mock
    0.41
    0.41
     Mock
    0.39
    tail
    0.38
    дня
    0.38
     mocked
    0.38
    χεί
    0.37
    Mississippi
    0.37
    Act Density 0.006%

    No Known Activations