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

    Neuronpedia

    INDEX
    Explanations

    neighborly relationships and disputes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    1.11
     are
    1.11
    ق
    1.11
     pesquis
    1.04
    ın
    1.03
    م
    1.02
     notizie
    0.98
     zijn
    0.94
     seria
    0.93
     يُ
    0.91
    POSITIVE LOGITS
    ور
    1.31
    -
    1.30
     neighbors
    1.18
    ли
    1.16
     neighbor
    1.10
    지는
    1.09
    एम
    1.08
    ਰ
    1.08
    neighbor
    1.01
    ರ
    1.01
    Act Density 0.007%

    No Known Activations