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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нося
    -0.07
    inth
    -0.07
    sie
    -0.07
     validated
    -0.06
     Comedy
    -0.06
     <%
    -0.06
     cruz
    -0.06
    .lp
    -0.06
     　 　 　 　 　
    -0.06
    .fil
    -0.06
    POSITIVE LOGITS
    utive
    0.07
     вихов
    0.07
    hammad
    0.07
     İs
    0.06
     newList
    0.06
    asurer
    0.06
    емого
    0.06
    ίνεται
    0.06
    ωση
    0.06
    ılacak
    0.06
    Act Density 0.075%

    No Known Activations