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

    Neuronpedia

    INDEX
    Explanations

    single digit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آیات
    1.52
    ش
    1.51
     elytris
    1.35
    های
    1.34
    bbene
    1.33
     regelmatig
    1.30
    ను
    1.30
     Dieses
    1.30
    ج
    1.25
    一番
    1.23
    POSITIVE LOGITS
    씩
    1.37
    istic
    1.22
    சே
    1.20
    EN
    1.15
    st
    1.13
     এদিকে
    1.13
     whis
    1.11
    istically
    1.04
     Range
    1.02
    еры
    1.02
    Act Density 0.496%

    No Known Activations