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

    Neuronpedia

    INDEX
    Explanations

    are attuned, Accounting menu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinnacle
    0.44
     Tango
    0.38
     Pinnacle
    0.38
    潑
    0.38
    得分
    0.37
    િવસે
    0.37
     সম্ভব
    0.37
     intenso
    0.37
     Tind
    0.36
     F
    0.36
    POSITIVE LOGITS
     দী
    0.45
    ?");
    0.41
    iee
    0.40
     بى
    0.38
    notas
    0.38
    ...");
    0.38
     greed
    0.38
     ");
    0.37
    text
    0.37
     blue
    0.37
    Act Density 0.000%

    No Known Activations