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

    Neuronpedia

    INDEX
    Explanations

    unnecessary variables, imports, complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    2.60
    atches
    2.56
    া
    2.52
    a
    2.52
    Voting
    2.45
    িম
    2.41
     totiž
    2.35
    𝗈
    2.29
    𝚞
    2.29
    ɱ
    2.26
    POSITIVE LOGITS
    ตรฐาน
    2.38
    নি
    2.33
    😂😂
    2.26
     menjel
    2.23
     শুভ
    2.11
     Diakses
    2.10
    warna
    2.08
    ھی
    2.05
    weisung
    2.03
    lete
    2.01
    Act Density 0.015%

    No Known Activations