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

    Neuronpedia

    INDEX
    Explanations

    ritual and ceremony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    1.17
    )
    1.16
    '
    1.15
    :
    1.14
    ,
    1.10
     the
    1.03
     trigonometric
    1.03
     masterpiece
    1.02
    .
    1.02
    -
    1.02
    POSITIVE LOGITS
     цере
    1.02
    ведите
    1.01
    ్‌
    0.99
    ак
    0.99
    ум
    0.94
    фу
    0.91
    <0x0D>
    0.91
    ал
    0.90
    }</
    0.88
    excluded
    0.88
    Act Density 0.003%

    No Known Activations