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

    Neuronpedia

    INDEX
    Explanations

    css declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    removeItem
    0.40
     bū
    0.38
    ᕝ
    0.38
     ссылку
    0.38
    ☻
    0.37
    водство
    0.37
    ifadə
    0.37
     विनियमन
    0.36
    urnal
    0.36
    ഴ്ച
    0.36
    POSITIVE LOGITS
     탄
    0.40
     efficiently
    0.36
    єм
    0.36
     диамет
    0.36
    DomainMask
    0.36
    夢
    0.35
    zący
    0.34
    識
    0.34
    Efficient
    0.34
     efficient
    0.34
    Act Density 0.001%

    No Known Activations