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

    Neuronpedia

    INDEX
    Explanations

    concepts and their related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chúng
    0.47
    いく
    0.46
    革命
    0.46
    Exerc
    0.45
    لا
    0.44
    Bismillahirrah
    0.44
    ᓲ
    0.43
    સમ
    0.43
     exercice
    0.42
    Z
    0.42
    POSITIVE LOGITS
     ticket
    0.42
     drunken
    0.42
     бил
    0.42
    ของการ
    0.42
     τησ
    0.42
     των
    0.41
     inefficient
    0.40
     κάθε
    0.40
     userID
    0.40
    水位
    0.40
    Act Density 0.009%

    No Known Activations