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

    Neuronpedia

    INDEX
    Explanations

    common determiner for nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    बरोबर
    0.67
     selected
    0.66
    importe
    0.64
     workflow
    0.63
    "{
    0.61
    MULTIP
    0.61
     આવે
    0.59
    writeValue
    0.58
    きたい
    0.58
     sélection
    0.57
    POSITIVE LOGITS
     sytuacji
    0.97
     daños
    0.92
     debts
    0.92
     injuries
    0.90
     Situation
    0.90
     Tablets
    0.89
     incidents
    0.89
     Witnesses
    0.88
     allegations
    0.87
     accusations
    0.87
    Act Density 0.327%

    No Known Activations