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

    Neuronpedia

    INDEX
    Explanations

    Trademarks and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oppression
    0.63
     solemn
    0.63
     robbing
    0.56
    言い
    0.55
     oppressive
    0.54
     feelings
    0.53
     passions
    0.53
     sende
    0.52
     palp
    0.52
     distress
    0.52
    POSITIVE LOGITS
    ®
    1.14
    Ⓡ
    1.09
    ®,
    1.05
    ™
    1.04
    ®.
    1.01
     Version
    0.97
    Plus
    0.96
     Plus
    0.95
     версии
    0.95
     phiên
    0.94
    Act Density 1.058%

    No Known Activations