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

    Neuronpedia

    INDEX
    Explanations

    pronoun wanting or recommending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     truc
    0.46
     deng
    0.40
     ho
    0.39
     del
    0.38
     mne
    0.37
    ade
    0.35
     Ho
    0.35
     치
    0.35
     adequacy
    0.35
    mode
    0.34
    POSITIVE LOGITS
     pending
    0.45
     highlight
    0.42
     sottoline
    0.41
     تقول
    0.41
     popularly
    0.41
     よろしく
    0.41
    平常
    0.40
     পড়ার
    0.39
    காற்று
    0.39
     quiero
    0.39
    Act Density 0.003%

    No Known Activations