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

    Neuronpedia

    INDEX
    Explanations

    Russian and English professional contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eqn
    0.48
     renseignements
    0.48
    ôs
    0.46
     acidente
    0.46
    infile
    0.46
    avement
    0.45
    television
    0.45
    itôt
    0.45
     numai
    0.44
    clinton
    0.44
    POSITIVE LOGITS
     актуа
    0.78
     осозна
    0.73
     контек
    0.72
     кей
    0.71
     комфор
    0.70
     формат
    0.66
     эмоциона
    0.66
     максимально
    0.64
     алгорит
    0.64
     адап
    0.64
    Act Density 0.009%

    No Known Activations