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

    Neuronpedia

    INDEX
    Explanations

    explanation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     domicili
    -0.08
     hobbies
    -0.08
    -0.08
    GEST
    -0.07
     నివ
    -0.07
     ব্যব
    -0.07
     Wohnung
    -0.07
     incorpora
    -0.07
     defe
    -0.07
     destinat
    -0.07
    POSITIVE LOGITS
     erläut
    0.12
    Explanation
    0.11
     توض
    0.10
     설명
    0.10
     подробно
    0.10
     explanation
    0.10
    説明
    0.10
     пояс
    0.10
     elabor
    0.10
     uitleg
    0.10
    Act Density 0.022%
    No Known Activations