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

    Neuronpedia

    INDEX
    Explanations

    Iraq

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SUMMARY
    -0.07
     ferv
    -0.07
     (_)
    -0.07
     여기
    -0.07
     theology
    -0.07
    ener
    -0.06
     sidl
    -0.06
     sixth
    -0.06
     Fleming
    -0.06
    Token
    -0.06
    POSITIVE LOGITS
     Iraq
    0.09
    Iraq
    0.08
    Matt
    0.08
    .ReadInt
    0.06
    Oregon
    0.06
     Matt
    0.06
     Bucc
    0.06
     العراق
    0.06
    .Bad
    0.06
     욕
    0.06
    Act Density 0.003%

    No Known Activations