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

    Neuronpedia

    INDEX
    Explanations

    sequence terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).
    0.45
    _
    0.44
    )
    0.44
    ),
    0.43
    atif
    0.37
    ak
    0.37
    ud
    0.37
     dette
    0.37
    iqueness
    0.36
     ሌሎች
    0.36
    POSITIVE LOGITS
    Từ
    0.38
     Tetapi
    0.38
    Чтобы
    0.37
    ك
    0.36
    UCLEAR
    0.36
     ngunit
    0.36
    ловой
    0.35
     transportasi
    0.35
    できる
    0.34
    千
    0.34
    Act Density 0.416%

    No Known Activations