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

    Neuronpedia

    INDEX
    Explanations

    advantage or edge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ohia
    0.81
    ব্য
    0.69
     politics
    0.68
    Reject
    0.67
     комментария
    0.65
     Politics
    0.62
     किडनी
    0.62
    askin
    0.62
     rejected
    0.62
    ቆ
    0.62
    POSITIVE LOGITS
     advantage
    3.45
    advantage
    3.13
     advantages
    2.97
     Advantage
    2.93
     ventaja
    2.92
     Advantages
    2.79
     disadvantage
    2.75
     vantagem
    2.73
     avantage
    2.63
    Advantages
    2.62
    Act Density 0.185%

    No Known Activations