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

    Neuronpedia

    INDEX
    Explanations

    optimizing or frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eventuali
    0.43
     schoolchildren
    0.40
     certains
    0.40
     അനുഭവ
    0.39
     pourra
    0.39
    ementia
    0.39
    0.39
     tutoring
    0.38
     natale
    0.38
     activity
    0.38
    POSITIVE LOGITS
     оптими
    0.45
     стара
    0.43
     PROP
    0.43
    往往
    0.41
     usually
    0.41
    often
    0.40
     often
    0.38
    锅
    0.38
     optimize
    0.38
     najlepiej
    0.38
    Act Density 0.001%

    No Known Activations