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

    Neuronpedia

    INDEX
    Explanations

    establishing a theme:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multimedia
    1.13
     சுற்றுச்சூழல்
    0.98
     imprese
    0.97
     nonprofit
    0.96
     Datenschutz
    0.96
    零部件
    0.94
     funzionamento
    0.94
    RETURNTRANSFER
    0.93
     дворе
    0.93
     혁
    0.93
    POSITIVE LOGITS
     sniper
    0.94
    aggressive
    0.92
     agres
    0.91
     aggressively
    0.86
     aggressiveness
    0.86
    early
    0.85
     early
    0.85
     aggressive
    0.83
    进攻
    0.83
    狙
    0.82
    Act Density 0.499%

    No Known Activations