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
    定的
    -0.07
    $_
    -0.06
    Esta
    -0.06
     tây
    -0.06
    Estado
    -0.06
     satu
    -0.06
    (lhs
    -0.06
    ovaného
    -0.06
     yandan
    -0.06
    Đây
    -0.06
    POSITIVE LOGITS
    logue
    0.07
     Mister
    0.07
     incidence
    0.07
     twitter
    0.06
    atherine
    0.06
    "time
    0.06
    amental
    0.06
    endar
    0.06
    .notification
    0.06
     Reader
    0.06
    Act Density 0.009%

    No Known Activations