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

    Neuronpedia

    INDEX
    Explanations

    ages and grade levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Amin
    0.44
     qDebug
    0.41
    name
    0.40
    窨
    0.39
    appName
    0.38
    ˆ‚
    0.37
    বাদী
    0.36
    ल्लिंग
    0.36
     diğer
    0.35
    Name
    0.35
    POSITIVE LOGITS
     level
    0.66
     onwards
    0.54
     niveau
    0.53
     مستوى
    0.53
    niveau
    0.52
     (<
    0.51
     পর্যা
    0.51
    부터
    0.50
     etapa
    0.50
     düzey
    0.49
    Act Density 0.257%

    No Known Activations