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

    Neuronpedia

    INDEX
    Explanations

    instruction following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fore
    0.85
     merupakan
    0.84
     существуют
    0.83
     ஏற்ப
    0.83
     worst
    0.83
     pong
    0.81
     gross
    0.79
    ঁজ
    0.78
     排
    0.78
     thống
    0.77
    POSITIVE LOGITS
    ships
    1.14
    dy
    1.05
    জি
    1.00
    dh
    0.96
    shire
    0.96
    nm
    0.93
    ীয়
    0.93
    ς
    0.93
     फैलाने
    0.93
     Rxb
    0.91
    Act Density 0.046%

    No Known Activations