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

    Neuronpedia

    INDEX
    Explanations

    Character encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的一
    -0.07
    /functions
    -0.07
    -nil
    -0.07
    变得
    -0.06
    _TODO
    -0.06
     ade
    -0.06
     gı
    -0.06
    :pk
    -0.06
     createAction
    -0.06
    .tbl
    -0.06
    POSITIVE LOGITS
     RA
    0.07
     suspend
    0.07
     reign
    0.07
    Alpha
    0.07
     Pillow
    0.07
    работка
    0.06
     нас
    0.06
     outbreak
    0.06
     LW
    0.06
     elevated
    0.06
    Act Density 0.003%

    No Known Activations