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

    Neuronpedia

    INDEX
    Explanations

    refugee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     atuação
    -0.08
    �
    -0.08
    �
    -0.08
    ชา
    -0.07
     ягод
    -0.07
    .NULL
    -0.07
    不存在
    -0.07
     drz
    -0.07
    بيه
    -0.07
     অনুভ
    -0.07
    POSITIVE LOGITS
     refugees
    0.13
     refugee
    0.11
     Flücht
    0.11
     influx
    0.10
     migrant
    0.10
     refugi
    0.09
     прибы
    0.09
     Refuge
    0.09
     humanitarian
    0.09
     fleeing
    0.09
    Act Density 0.017%

    No Known Activations