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

    Neuronpedia

    INDEX
    Explanations

    bot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amask
    0.44
     thieves
    0.43
    ingly
    0.42
    რა
    0.41
    ategories
    0.41
     Сол
    0.41
    órias
    0.41
     providers
    0.40
     вас
    0.40
    ourcen
    0.40
    POSITIVE LOGITS
     bot
    0.53
     Bot
    0.49
    bot
    0.47
    Bot
    0.45
    BOT
    0.42
     BOT
    0.42
     periód
    0.39
    屿
    0.37
    diameter
    0.37
    arelli
    0.37
    Act Density 0.010%

    No Known Activations