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

    Neuronpedia

    INDEX
    Explanations

    web addresses and hosting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     redemption
    0.79
     Redemption
    0.67
     bipartisan
    0.64
    ุทธ
    0.63
     Severity
    0.63
     bassin
    0.60
     DMA
    0.60
     audit
    0.60
     audits
    0.59
    定律
    0.59
    POSITIVE LOGITS
    herokuapp
    1.01
    hosting
    0.88
     hosting
    0.86
    띄
    0.86
     Hosting
    0.85
    ipage
    0.85
    netlify
    0.83
    localhost
    0.82
    hosted
    0.82
    LOCALHOST
    0.81
    Act Density 0.593%

    No Known Activations