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

    Neuronpedia

    INDEX
    Explanations

    Lake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prop
    -0.08
    免疫
    -0.07
     transportation
    -0.07
    rn
    -0.07
    arbon
    -0.07
    הצע
    -0.07
    енн
    -0.07
    Seleccion
    -0.07
    人社
    -0.06
    Newsletter
    -0.06
    POSITIVE LOGITS
    压制
    0.08
     jealous
    0.07
    ทะเล
    0.07
    体制机制
    0.07
    חמד
    0.07
     childish
    0.07
     PIT
    0.07
     militias
    0.07
    捨て
    0.07
    尻
    0.07
    Act Density 0.014%

    No Known Activations