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

    Neuronpedia

    INDEX
    Explanations

    security personnel, patrol, presence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ैमर
    1.09
    áu
    1.05
    ställ
    1.05
    ummy
    1.04
    ங்க்
    1.02
    சு
    1.01
     sprzedaży
    0.98
     është
    0.97
    ஸ்
    0.97
    esis
    0.96
    POSITIVE LOGITS
    ف
    1.73
    ا
    1.24
    ح
    1.02
     patrolling
    1.01
    I
    0.99
    ı
    0.99
     I
    0.99
    력이
    0.99
     patrols
    0.98
    ю
    0.97
    Act Density 0.146%

    No Known Activations