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

    Neuronpedia

    INDEX
    Explanations

    introductions and starting conversations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    যা
    0.38
     ща
    0.37
     আবে
    0.36
    opre
    0.36
    <0xA0>
    0.35
    র্পণ
    0.35
     Huber
    0.34
    मील
    0.34
    aphys
    0.34
    GW
    0.33
    POSITIVE LOGITS
     introductions
    2.23
     introduce
    2.08
     introduction
    2.00
     Introdu
    2.00
     Introduce
    2.00
     introdu
    1.95
    Introduce
    1.91
     memperkenalkan
    1.90
    introdu
    1.86
    introduce
    1.86
    Act Density 0.110%

    No Known Activations