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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inke
    -0.07
     виб
    -0.07
    Invoice
    -0.07
     wager
    -0.06
     editar
    -0.06
    inde
    -0.06
     závě
    -0.06
    十五
    -0.06
    179
    -0.06
     UNIVERS
    -0.06
    POSITIVE LOGITS
    ierce
    0.07
     BSON
    0.07
    Good
    0.06
    (...)↵
    0.06
     isKindOfClass
    0.06
    ries
    0.06
     ihtiyac
    0.06
    :first
    0.06
     DataContext
    0.06
    _UID
    0.06
    Act Density 0.041%

    No Known Activations