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

    Neuronpedia

    INDEX
    Explanations

    Google Assistant and voice assistants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    浣
    0.39
    chatbot
    0.39
    ўным
    0.39
     పథ
    0.38
    理想
    0.38
     пера
    0.38
    Ideally
    0.38
     предполага
    0.38
    장을
    0.37
    法轮
    0.37
    POSITIVE LOGITS
     speaker
    0.54
     microphone
    0.49
     booms
    0.46
     loudspeaker
    0.46
     Assistant
    0.44
     Speaker
    0.44
     audio
    0.43
     boom
    0.43
    Speaker
    0.43
     headphones
    0.42
    Act Density 0.016%

    No Known Activations