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

    Neuronpedia

    INDEX
    Explanations

    military invasion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    K
    0.96
    ：
    0.94
     നൽക
    0.89
    ।,
    0.87
     。,
    0.86
    ק
    0.85
     μία
    0.84
    c
    0.83
    鹕
    0.82
    ができる
    0.81
    POSITIVE LOGITS
    (
    1.13
     invasion
    1.10
     Invasion
    1.02
    \
    1.01
    vasion
    0.97
    erne
    0.87
    {
    0.86
     invasions
    0.82
    ation
    0.80
     by
    0.80
    Act Density 0.003%

    No Known Activations