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

    Neuronpedia

    INDEX
    Explanations

    standard operating procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     находиться
    0.54
    я
    0.48
    o
    0.47
     четы
    0.46
    YAN
    0.45
    నే
    0.44
     Affiliate
    0.44
     Sim
    0.44
     A
    0.43
    ीय
    0.43
    POSITIVE LOGITS
     montrer
    0.48
     medlem
    0.46
     montre
    0.46
     militaires
    0.45
    ackets
    0.45
     ತೋರಿಸ
    0.44
    Mf
    0.44
     sneakers
    0.44
    erna
    0.43
     montrent
    0.43
    Act Density 0.001%

    No Known Activations