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

    Neuronpedia

    INDEX
    Explanations

    800 numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    インタ
    0.41
    䄪
    0.40
    '),
    0.38
    ურთიერთ
    0.37
    救
    0.37
    "),
    0.37
    ರಿಗೆ
    0.36
     betrayal
    0.36
     supposing
    0.36
    »),
    0.36
    POSITIVE LOGITS
     toll
    0.67
     Toll
    0.59
    toll
    0.54
     tolls
    0.49
     टोल
    0.45
     tolle
    0.43
     бел
    0.42
     Zentr
    0.39
    ittäin
    0.39
    ଣ୍
    0.39
    Act Density 0.028%

    No Known Activations