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

    Neuronpedia

    INDEX
    Explanations

    International relations/territories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gly
    -0.09
    奋
    -0.08
    奖金
    -0.08
    ومي
    -0.08
     sexta
    -0.08
     柳
    -0.08
    senha
    -0.08
     Prep
    -0.08
    oxetine
    -0.08
     fibonacci
    -0.08
    POSITIVE LOGITS
     treaty
    0.12
     विवाद
    0.11
     refugees
    0.10
     cadas
    0.10
     disputed
    0.10
     contentious
    0.10
    双方
    0.10
     diplom
    0.10
     Treaty
    0.10
     Palestinians
    0.09
    Act Density 0.016%

    No Known Activations