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

    Neuronpedia

    INDEX
    Explanations

    lost, dungeon, desert, exploring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     @
    0.66
     #
    0.48
     %
    0.48
     sepd
    0.47
    咱们
    0.45
     docs
    0.44
     đc
    0.44
    ுள்ளது
    0.44
     Twitter
    0.43
     &
    0.42
    POSITIVE LOGITS
     enjoying
    0.71
    Sometimes
    0.59
    Exploring
    0.54
     posing
    0.54
     Просто
    0.50
    Enjoy
    0.50
     menikmati
    0.49
    享受
    0.48
    trying
    0.48
     иногда
    0.48
    Act Density 0.003%

    No Known Activations