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

    Neuronpedia

    INDEX
    Explanations

    request for input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     combines
    0.37
     laying
    0.36
     endowment
    0.35
     conferred
    0.34
     stains
    0.33
     cuts
    0.33
     alleles
    0.33
     vineyards
    0.33
     merino
    0.32
     fluvial
    0.32
    POSITIVE LOGITS
     말투
    0.53
     질문
    0.52
     reply
    0.51
     अनुरोध
    0.48
    请求
    0.46
     पूछी
    0.45
    質問
    0.45
     प्रतिसाद
    0.44
     chatbot
    0.44
     요청
    0.44
    Act Density 1.908%

    No Known Activations