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

    Neuronpedia

    INDEX
    Explanations

    ratings/scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhiên
    -0.07
    获
    -0.06
     Empty
    -0.06
     Prometheus
    -0.06
    AWS
    -0.06
    ίνεται
    -0.06
    .room
    -0.06
    .questions
    -0.06
    desktop
    -0.06
     IPs
    -0.06
    POSITIVE LOGITS
     till
    0.08
    되지
    0.07
    iationException
    0.07
     Перед
    0.07
    paněl
    0.07
     reaff
    0.07
    usher
    0.06
    aniel
    0.06
    ····
    0.06
     превыш
    0.06
    Act Density 0.046%

    No Known Activations