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

    Neuronpedia

    INDEX
    Explanations

    rate of, limiting, hikes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்
    0.55
    ی
    0.51
    ים
    0.49
    ი
    0.46
    ждения
    0.46
    ्रल
    0.46
    AZIONE
    0.46
     রাষ্ট্রের
    0.46
    मूल
    0.46
    ສາມາດ
    0.45
    POSITIVE LOGITS
    payer
    0.79
     hike
    0.49
     climb
    0.49
     sheet
    0.48
    kin
    0.46
     hikes
    0.45
    geber
    0.45
     card
    0.45
     CARD
    0.43
    card
    0.43
    Act Density 0.025%

    No Known Activations