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

    Neuronpedia

    INDEX
    Explanations

    saying goodbye to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    0.85
    )
    0.79
    »
    0.77
    0.75
     It
    0.75
    ),
    0.74
    ).
    0.72
     ilust
    0.70
            
    0.70
    _
    0.70
    POSITIVE LOGITS
    to
    1.05
     farewell
    1.03
     goodbye
    0.94
    ین
    0.80
    Goodbye
    0.77
    지
    0.77
     desped
    0.74
    ного
    0.73
    ан
    0.71
    िक
    0.70
    Act Density 0.007%

    No Known Activations