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

    Neuronpedia

    INDEX
    Explanations

    conversations and thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kawaii
    0.79
     fornecer
    0.79
     proporcionan
    0.78
     minions
    0.73
     bebas
    0.71
     fornire
    0.71
     ottenere
    0.70
     chibi
    0.70
     aby
    0.70
     controllare
    0.70
    POSITIVE LOGITS
     चिंतन
    0.92
     conversations
    0.91
     Conversations
    0.89
    Conversation
    0.89
    Thinking
    0.86
    思考
    0.84
    Insights
    0.84
    Convers
    0.82
     Conversation
    0.80
    Talking
    0.80
    Act Density 0.441%

    No Known Activations