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

    Neuronpedia

    INDEX
    Explanations

    qualified withdrawals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acji
    0.47
    https
    0.44
     commence
    0.44
     commencement
    0.44
    Install
    0.43
    </h2>
    0.42
    </h3>
    0.42
     juin
    0.42
    PL
    0.42
     tantas
    0.42
    POSITIVE LOGITS
     مع
    0.50
     Urinary
    0.46
    橡胶
    0.44
    రించే
    0.43
    jacke
    0.43
    䘚
    0.43
    ಗಳ
    0.42
     తిన
    0.41
    పరి
    0.41
     اسئله
    0.41
    Act Density 0.007%

    No Known Activations