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

    Neuronpedia

    INDEX
    Explanations

    polyethylene glycol (PEG)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ט
    0.73
    et
    0.68
    es
    0.67
    el
    0.65
    ia
    0.65
     toast
    0.65
    ie
    0.62
    bhl
    0.61
    ক্লা
    0.59
    不少
    0.59
    POSITIVE LOGITS
    その
    0.70
     Sovi
    0.67
    पी
    0.67
     塩
    0.67
    寒い
    0.64
     परमात्मा
    0.63
    ప్పటి
    0.61
    یت
    0.61
    この
    0.61
    ୍କ
    0.61
    Act Density 0.002%

    No Known Activations