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

    Neuronpedia

    INDEX
    Explanations

    foundational and practical topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LocalizedString
    0.43
    Hemos
    0.42
    一声
    0.41
    encrypted
    0.40
     fece
    0.40
     പറഞ്ഞ
    0.39
    利的
    0.39
     rebounds
    0.38
    filename
    0.38
    PhoneNumber
    0.38
    POSITIVE LOGITS
     taught
    0.88
     topics
    0.84
     Topics
    0.82
     fundamentals
    0.80
     aprender
    0.77
    Topics
    0.77
     Practical
    0.77
     mastering
    0.77
     foundational
    0.77
     practical
    0.76
    Act Density 0.064%

    No Known Activations