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

    Neuronpedia

    INDEX
    Explanations

    music, games, and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    understood
    0.41
    events
    0.39
    event
    0.38
    cephalus
    0.38
     aldosterone
    0.38
     conserver
    0.37
     understood
    0.37
     события
    0.37
    quantity
    0.37
     regenerate
    0.36
    POSITIVE LOGITS
     karaoke
    0.91
     games
    0.86
     노래
    0.86
     Karaoke
    0.83
     quiz
    0.80
     discussion
    0.80
     singing
    0.79
     muziek
    0.79
     Quiz
    0.78
     juegos
    0.78
    Act Density 0.019%

    No Known Activations