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

    Neuronpedia

    INDEX
    Explanations

    Wisconsin/Washington

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有一次
    -0.07
    lightbox
    -0.07
     unsur
    -0.07
    �
    -0.07
    (QL
    -0.07
    ",{
    -0.07
    驼
    -0.07
     dispersed
    -0.06
    蔺
    -0.06
    מצרים
    -0.06
    POSITIVE LOGITS
    brook
    0.07
    _coeff
    0.07
    ivity
    0.07
     livre
    0.07
    媓
    0.06
     på
    0.06
    航空
    0.06
    (process
    0.06
    .Driver
    0.06
     Bowen
    0.06
    Act Density 0.003%

    No Known Activations