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

    Neuronpedia

    INDEX
    Explanations

    by [author name]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    1.53
    ដល់
    1.44
    دت
    1.35
    一个
    1.35
    $.
    1.34
    a
    1.28
    端末
    1.25
    เรื่อง
    1.24
     ৭৭
    1.22
     நடத்திய
    1.18
    POSITIVE LOGITS
    ು
    2.14
     flaves
    1.53
     recherche
    1.47
     ост
    1.45
     সভায়
    1.44
    िंग
    1.44
    লিখ
    1.41
    igarh
    1.41
    ี
    1.40
     FirebaseAuth
    1.39
    Act Density 0.012%

    No Known Activations