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

    Neuronpedia

    INDEX
    Explanations

    disparagement and discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contrasts
    0.59
    ナソニック
    0.59
     nonprofits
    0.56
     recreating
    0.56
     activism
    0.55
     probationary
    0.55
     ثقاف
    0.55
     credibility
    0.54
     oncology
    0.54
    ariously
    0.54
    POSITIVE LOGITS
     jika
    1.05
     diperoleh
    1.00
     persamaan
    1.00
     Jika
    0.97
     nilai
    0.94
     dengan
    0.93
     adalah
    0.93
     jumlah
    0.91
     pernyataan
    0.90
     berdasarkan
    0.89
    Act Density 0.001%

    No Known Activations