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

    Neuronpedia

    INDEX
    Explanations

    G7 or Council ministers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ust
    1.08
    jor
    0.95
    ur
    0.90
    te
    0.85
    bih
    0.84
    ته
    0.83
    υ
    0.82
    ben
    0.81
    oman
    0.81
     करण्यासाठी
    0.81
    POSITIVE LOGITS
     peels
    0.98
    ็
    0.88
     Travels
    0.87
     pebbles
    0.86
     textes
    0.86
    牪
    0.85
     heads
    0.84
     wallpapers
    0.84
     خانم
    0.84
     keyValue
    0.84
    Act Density 0.004%

    No Known Activations