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
    郭
    -0.07
     niž
    -0.07
    าพ
    -0.07
    Dealer
    -0.07
    esub
    -0.06
    atab
    -0.06
    MDB
    -0.06
    )null
    -0.06
    crm
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     primeiro
    0.07
     Video
    0.06
    _annotation
    0.06
     contradiction
    0.06
     Stuart
    0.06
    _done
    0.06
    私は
    0.06
     цвет
    0.06
     Agreement
    0.06
     призна
    0.06
    Act Density 0.015%

    No Known Activations