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

    Neuronpedia

    INDEX
    Explanations

    software license versions (v2, v3)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺮ
    0.43
     جگہ
    0.40
    اسة
    0.40
     میں
    0.39
    but
    0.39
    ند
    0.39
    ја
    0.39
    ليب
    0.39
    ifikasi
    0.39
    ")}
    0.39
    POSITIVE LOGITS
    Single
    0.44
    SCE
    0.43
     cellulosic
    0.43
    ULATORY
    0.43
     MFC
    0.43
    MFC
    0.42
     SCE
    0.42
     RPC
    0.41
    Sweep
    0.41
     ጥላ
    0.41
    Act Density 0.001%

    No Known Activations