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

    Neuronpedia

    INDEX
    Explanations

    good at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    秽
    0.44
    Scheduler
    0.43
     troops
    0.41
     scheduler
    0.39
    કામાં
    0.39
     racing
    0.38
     homes
    0.38
     είναι
    0.38
     track
    0.38
     planner
    0.37
    POSITIVE LOGITS
    ຈະ
    0.40
     உருவா
    0.39
    구나
    0.39
    简直
    0.39
     Vielleicht
    0.38
    🤪
    0.38
    sthresh
    0.38
    曳
    0.38
     Oxygen
    0.38
     Fitz
    0.37
    Act Density 0.000%

    No Known Activations