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

    Neuronpedia

    INDEX
    Explanations

    SEC filings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     می‌توان
    0.65
    ‌ای
    0.61
     باید
    0.60
     facilmente
    0.60
     بی‌
    0.60
     ہیں
    0.59
     potrebbero
    0.59
     می‌شوند
    0.59
     possono
    0.58
     کمپیو
    0.57
    POSITIVE LOGITS
     filings
    0.66
     Filing
    0.59
     filing
    0.56
     filed
    0.54
     США
    0.52
     films
    0.45
     offici
    0.45
    <h4>
    0.45
    ൊപ്പം
    0.44
    owym
    0.44
    Act Density 0.006%

    No Known Activations