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

    Neuronpedia

    INDEX
    Explanations

    discrepancy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (NUM
    -0.07
     immigrants
    -0.07
    EAR
    -0.07
     ratio
    -0.06
     /[
    -0.06
     Latitude
    -0.06
     apo
    -0.06
     thor
    -0.06
     národ
    -0.06
     Stafford
    -0.06
    POSITIVE LOGITS
     baj
    0.07
    バイ
    0.07
    ğinde
    0.07
    ENS
    0.07
     checking
    0.07
    ้อง
    0.07
     مشکل
    0.07
    ик
    0.07
     Peach
    0.07
    جاج
    0.07
    Act Density 0.013%

    No Known Activations