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

    Neuronpedia

    INDEX
    Explanations

    list items or steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     парла
    0.95
    Kamu
    0.91
    Queen
    0.83
    Project
    0.76
    Sphere
    0.76
    Casa
    0.76
    Zone
    0.76
    Stake
    0.75
    Ḫ
    0.75
    Vamos
    0.74
    POSITIVE LOGITS
     resonates
    0.88
    ما
    0.82
     resonate
    0.81
    ها
    0.77
     ❤
    0.73
     tenter
    0.72
     accuracies
    0.70
     '['
    0.70
    ສົ່ງ
    0.69
     substantiate
    0.69
    Act Density 0.090%

    No Known Activations