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

    Neuronpedia

    INDEX
    Explanations

    magic square, binary case, city values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Financial
    0.53
    I
    0.50
    с
    0.50
    financial
    0.45
    financ
    0.45
    ра
    0.44
    ুরি
    0.44
    ре
    0.44
    Father
    0.44
    mutual
    0.43
    POSITIVE LOGITS
     acutely
    0.49
     частности
    0.48
     accompanies
    0.46
     शीर्षक
    0.46
     alluded
    0.46
     earnestly
    0.46
     aptly
    0.45
     Abstracts
    0.45
     افزایش
    0.45
     subtleties
    0.45
    Act Density 0.004%

    No Known Activations