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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    馌
    -0.08
     GDK
    -0.07
     preceded
    -0.07
    and
    -0.07
     denen
    -0.07
     approaching
    -0.06
    with
    -0.06
     tion
    -0.06
     hk
    -0.06
     der
    -0.06
    POSITIVE LOGITS
    inherit
    0.07
    〷
    0.07
     Britann
    0.06
    不管是
    0.06
     Offline
    0.06
    为了更好
    0.06
    &oacute
    0.06
    細
    0.06
    💿
    0.06
     Quận
    0.06
    Act Density 0.003%

    No Known Activations