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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     завдання
    -0.07
    -language
    -0.07
    μέ
    -0.06
     نقشه
    -0.06
     norms
    -0.06
     допомоги
    -0.06
    _track
    -0.06
     instancia
    -0.06
    _serial
    -0.06
    _detalle
    -0.06
    POSITIVE LOGITS
     gover
    0.07
    ’:
    0.07
    :Set
    0.07
    ẩn
    0.07
     …↵
    0.06
     mean
    0.06
     uint
    0.06
    vik
    0.06
    153
    0.06
    evaluate
    0.06
    Act Density 0.001%

    No Known Activations