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

    Neuronpedia

    INDEX
    Explanations

    universities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ンド
    -0.07
    ев
    -0.07
    inia
    -0.06
    iaux
    -0.06
    anne
    -0.06
    ird
    -0.06
    uyết
    -0.06
    ichel
    -0.06
    iones
    -0.06
    ‐
    -0.06
    POSITIVE LOGITS
     springfox
    0.08
     登
    0.07
    复试
    0.07
    FromClass
    0.07
    �
    0.07
    贯穿
    0.07
    取决
    0.07
     occas
    0.07
    念头
    0.06
    拿到了
    0.06
    Act Density 0.037%

    No Known Activations