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

    Neuronpedia

    INDEX
    Explanations

    as possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +
    0.37
     bialgebras
    0.35
    ’
    0.32
    +)
    0.31
    e
    0.29
    -/
    0.29
    3
    0.29
    ][
    0.29
    achs
    0.29
    /
    0.28
    POSITIVE LOGITS
     in
    0.34
     بالنسبة
    0.33
     जब
    0.31
     tentang
    0.31
     بالنسبه
    0.30
     अबाउट
    0.30
    ใน
    0.29
     about
    0.28
     क्योंकि
    0.28
    hubungan
    0.27
    Act Density 0.184%

    No Known Activations