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

    Neuronpedia

    INDEX
    Explanations

    Laura followed by surname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     搞笑
    -0.92
    umentos
    -0.87
     preva
    -0.87
     SPS
    -0.84
    Haben
    -0.83
     frança
    -0.83
     himself
    -0.83
    姈
    -0.83
     kolejne
    -0.82
    uestion
    -0.81
    POSITIVE LOGITS
     Jean
    1.03
     Jane
    0.90
     Maria
    0.88
     Lee
    0.84
     Mae
    0.84
     bel
    0.82
     add
    0.81
     Oh
    0.81
    Jean
    0.80
     tossing
    0.80
    Act Density 0.019%

    No Known Activations