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

    Neuronpedia

    INDEX
    Explanations

    AI chatbot disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зка
    0.74
    ൻസ്
    0.73
     tools
    0.69
    allItems
    0.67
    moires
    0.67
    arquía
    0.67
     guardar
    0.66
    躺
    0.65
    akse
    0.65
    šku
    0.65
    POSITIVE LOGITS
    bot
    1.05
    GPI
    0.90
    GBT
    0.84
    bots
    0.81
    gpt
    0.81
    room
    0.81
    పతి
    0.79
    机器人
    0.79
    Bot
    0.78
    GP
    0.78
    Act Density 0.023%

    No Known Activations