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

    Neuronpedia

    INDEX
    Explanations

    costly or expensive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lowest
    0.93
     Lowest
    0.87
    低于
    0.78
     Low
    0.77
    Low
    0.76
     низ
    0.75
    轻松
    0.73
     rendah
    0.73
    輕鬆
    0.72
     low
    0.70
    POSITIVE LOGITS
     expensive
    3.99
     costly
    3.53
     Expensive
    3.52
    Expensive
    3.29
     pricey
    3.29
    expensive
    3.12
     дорого
    2.76
     дорогие
    2.50
     महंगी
    2.41
     महंगे
    2.38
    Act Density 0.239%

    No Known Activations