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

    Neuronpedia

    INDEX
    Explanations

    navy and naval activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ुर
    1.05
    lar
    0.98
    ne
    0.96
    ुक
    0.92
    се
    0.91
    ي
    0.91
    𝗱
    0.91
     eben
    0.91
    ى
    0.90
    وفة
    0.90
    POSITIVE LOGITS
    스럽
    1.23
    Admiral
    1.22
    Sail
    1.15
     admiral
    1.11
    舰
    1.11
    स
    1.11
     MediaType
    1.11
    hmm
    1.09
     goles
    1.09
     battleship
    1.08
    Act Density 0.049%

    No Known Activations