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

    Neuronpedia

    INDEX
    Explanations

    Arabic numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tian
    0.68
    ⁤
    0.63
    ())+
    0.63
    🏛
    0.62
    ⟋
    0.62
     chatbots
    0.62
    🌄
    0.62
     Guang
    0.61
    ‑
    0.61
     extraordin
    0.61
    POSITIVE LOGITS
    q
    0.66
    ht
    0.63
    qa
    0.61
    pta
    0.60
    Z
    0.60
    xt
    0.59
    rt
    0.59
    W
    0.59
    X
    0.58
     العد
    0.58
    Act Density 0.362%

    No Known Activations