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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allies
    -0.06
     comes
    -0.06
    íš
    -0.06
     Campo
    -0.06
     đồ
    -0.06
    ,rp
    -0.06
     khi
    -0.06
     станов
    -0.06
     Comic
    -0.06
    罗斯
    -0.06
    POSITIVE LOGITS
    *A
    0.06
    ,output
    0.06
     �
    0.06
     narrowing
    0.06
    .reason
    0.06
     skipping
    0.06
    )?.
    0.06
     siguientes
    0.06
     metodo
    0.06
     �
    0.06
    Act Density 0.680%

    No Known Activations