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

    Neuronpedia

    INDEX
    Explanations

    anyone/everyone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     people
    -1.28
    people
    -1.00
     everyone
    -0.93
    People
    -0.90
    everyone
    -0.87
     Efq
    -0.86
     mensen
    -0.83
     PEOPLE
    -0.83
     anyone
    -0.81
     People
    -0.79
    POSITIVE LOGITS
     who
    0.70
     involved
    0.63
    '
    0.58
     whose
    0.54
    клопе
    0.53
    век
    0.52
     can
    0.51
    omon
    0.49
    </caption>
    0.48
    涯
    0.48
    Act Density 0.054%

    No Known Activations