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

    Neuronpedia

    INDEX
    Explanations

    grades and varieties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    职
    0.52
     Minimalism
    0.49
    众多
    0.43
     সন্ত্রাস
    0.43
    有关
    0.42
     क्रांतिकारी
    0.42
    简单
    0.41
     Innovative
    0.41
    语义
    0.41
    强大的
    0.41
    POSITIVE LOGITS
     varieties
    0.77
     grade
    0.76
     Grade
    0.75
     premium
    0.73
     variedades
    0.73
     сорта
    0.72
    品種
    0.69
     medium
    0.68
     grades
    0.68
    Grade
    0.66
    Act Density 0.030%

    No Known Activations