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

    Neuronpedia

    INDEX
    Explanations

    advisable or prudent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     인정
    0.69
     exquisite
    0.65
     reject
    0.65
     Stunning
    0.63
     sacred
    0.61
     이거
    0.61
     নাটক
    0.60
    ovací
    0.60
     unmistakable
    0.59
     tuku
    0.59
    POSITIVE LOGITS
     wise
    1.79
    wise
    1.34
     Wise
    1.34
     advisable
    1.29
     worth
    1.25
    Wise
    1.25
     prudent
    1.23
     warto
    1.16
     WISE
    1.13
     варто
    1.13
    Act Density 0.271%

    No Known Activations