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

    Neuronpedia

    INDEX
    Explanations

    playing games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     layering
    0.78
    Presentation
    0.74
     sdx
    0.74
    缚
    0.73
     transmettre
    0.69
     Teilnehmer
    0.69
     sonrisa
    0.69
    স্তে
    0.68
     plating
    0.68
    jelder
    0.67
    POSITIVE LOGITS
     hide
    1.03
     games
    1.02
     devil
    1.02
     havoc
    1.00
     cards
    0.98
     guitar
    0.95
    wright
    0.93
     chess
    0.93
     coy
    0.93
     Devil
    0.92
    Act Density 0.066%

    No Known Activations