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

    Neuronpedia

    INDEX
    Explanations

    legal filings and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jö
    0.73
    我们的
    0.70
     جهانی
    0.70
    重要
    0.69
    我們
    0.68
    Now
    0.66
     cytoplas
    0.66
    We
    0.65
    世界
    0.65
    faktor
    0.65
    POSITIVE LOGITS
     allegations
    1.05
     aggrieved
    0.95
     alleging
    0.94
     defendant
    0.94
     attorney
    0.89
     affidavits
    0.88
     alleges
    0.85
     grievances
    0.84
     petitions
    0.83
     Defendant
    0.82
    Act Density 0.097%

    No Known Activations