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

    Neuronpedia

    INDEX
    Explanations

    qualifyingrewarded or recognized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     travailler
    0.42
     dreamer
    0.40
     postdoc
    0.39
     setelah
    0.39
     стреми
    0.39
     ड्रग
    0.38
     debacle
    0.38
    ֒
    0.38
     tsunami
    0.38
    тта
    0.38
    POSITIVE LOGITS
     often
    0.39
     Certificates
    0.39
     비용
    0.38
     rewarded
    0.38
     encouraged
    0.38
     reinforced
    0.37
     detract
    0.37
     constitute
    0.37
     considered
    0.36
     constitutes
    0.36
    Act Density 0.021%

    No Known Activations