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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mü
    -0.07
    �
    -0.07
    fern
    -0.06
    imizi
    -0.06
    `s
    -0.06
    getState
    -0.06
    select
    -0.06
    larının
    -0.06
     марта
    -0.06
     vượt
    -0.06
    POSITIVE LOGITS
    中に
    0.06
    elial
    0.06
    Paginator
    0.06
    =msg
    0.06
     Ec
    0.05
    .removeChild
    0.05
    ществ
    0.05
     características
    0.05
    _contr
    0.05
     تواند
    0.05
    Act Density 0.054%

    No Known Activations