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

    Neuronpedia

    INDEX
    Explanations

    always respected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FBSDK
    0.68
     ติด
    0.68
     glycine
    0.67
     sealant
    0.66
     যোগদান
    0.66
     liegen
    0.65
    㫜
    0.64
    ഷ്‌
    0.64
     drows
    0.63
    léans
    0.63
    POSITIVE LOGITS
     respect
    4.22
    Respect
    3.91
     Respect
    3.86
     respecting
    3.76
    respect
    3.68
     respects
    3.66
     RESPECT
    3.50
    尊重
    3.27
     respeto
    3.22
     respected
    3.19
    Act Density 0.577%

    No Known Activations