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

    Neuronpedia

    INDEX
    Explanations

    As of late November today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ara
    1.59
     sebab
    1.48
    ﻪ
    1.48
    sourceforge
    1.34
    ez
    1.34
    EN
    1.29
    ATION
    1.28
    us
    1.27
    ou
    1.27
    ﻮ
    1.27
    POSITIVE LOGITS
    おお
    1.55
    اً
    1.48
    ح
    1.38
     rulers
    1.38
    льного
    1.32
    носи
    1.32
     robes
    1.27
    ного
    1.27
     gaskets
    1.27
    ্ম্ম
    1.26
    Act Density 0.006%

    No Known Activations