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

    Neuronpedia

    INDEX
    Explanations

    Conversational responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     we're
    -0.08
     rollover
    -0.08
    imination
    -0.08
    理念
    -0.08
    urie
    -0.07
     المنتجات
    -0.07
     EO
    -0.07
     عد
    -0.07
     مستق
    -0.07
     erad
    -0.07
    POSITIVE LOGITS
     메시
    0.09
     cheering
    0.09
    icy
    0.09
     congratulations
    0.09
     ट्वीट
    0.09
    返信
    0.09
    .MESSAGE
    0.09
     applause
    0.09
     संदेश
    0.09
    こんにちは
    0.09
    Act Density 0.011%

    No Known Activations