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

    Neuronpedia

    INDEX
    Explanations

    numbers and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ikopter
    0.19
     Bumble
    0.18
     whatnot
    0.18
     hypoallergenic
    0.18
     ट्रॉपिकल
    0.18
    mselves
    0.17
    为一个
    0.17
    âteau
    0.17
    ppling
    0.17
     Built
    0.17
    POSITIVE LOGITS
    6
    0.23
    5
    0.20
    4
    0.20
    7
    0.20
    愭
    0.19
    VALUE
    0.19
    3
    0.19
     کاسینو
    0.18
    ４
    0.18
    戞
    0.18
    Act Density 8.096%

    No Known Activations