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

    Neuronpedia

    INDEX
    Explanations

    oxides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ein
    -0.07
    做一些
    -0.07
    哈尔滨
    -0.07
    ак
    -0.07
     Bet
    -0.06
    ',{
    -0.06
     Orlando
    -0.06
    自此
    -0.06
     Honestly
    -0.06
    就被
    -0.06
    POSITIVE LOGITS
    씹
    0.08
    굳
    0.08
     supermarket
    0.07
    (*)(
    0.07
     plataforma
    0.07
     explanation
    0.07
    getDescription
    0.07
     '='
    0.07
    🌌
    0.07
    획
    0.07
    Act Density 0.008%

    No Known Activations