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

    Neuronpedia

    INDEX
    Explanations

    arrogant sund aver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     china
    -0.11
    pto
    -0.11
    ä¹Ĥ
    -0.11
    éĺħ读次æķ°
    -0.10
    china
    -0.10
    onga
    -0.10
    çĦ¡ãģĹãģ
    -0.09
     China
    -0.09
    Gov
    -0.09
    èĨľ
    -0.09
    POSITIVE LOGITS
    (æľ¨
    0.13
     sund
    0.12
     ausp
    0.11
    asser
    0.11
     gere
    0.10
    (æ°´
    0.10
    (çģ«
    0.09
     Bret
    0.09
     aver
    0.09
     arrog
    0.09
    Act Density 0.209%

    No Known Activations