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

    Neuronpedia

    INDEX
    Explanations

    punctuation and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಗೊಳ್ಳ
    0.78
     হিসেবে
    0.78
    供
    0.73
    maßen
    0.73
    囦
    0.73
     фа
    0.72
     кок
    0.71
    般的
    0.71
     તરીકે
    0.70
     செய்தால்
    0.70
    POSITIVE LOGITS
     αρκε
    0.75
     beaucoup
    0.73
     ett
    0.69
     mucho
    0.69
     steeds
    0.67
     a
    0.67
     μια
    0.66
     실제로
    0.65
     immer
    0.65
    는
    0.65
    Act Density 0.003%

    No Known Activations