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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    POINT
    -0.08
    :↵
    -0.07
    :]↵
    -0.07
    deploy
    -0.07
    قر
    -0.07
    Shared
    -0.07
     confirming
    -0.06
     Consumption
    -0.06
     tomar
    -0.06
    ].
    -0.06
    POSITIVE LOGITS
     ['$
    0.07
     neuen
    0.07
    .exchange
    0.06
     bem
    0.06
    _lista
    0.06
     нов
    0.06
     メ
    0.06
     درخواست
    0.06
    (cart
    0.06
     birçok
    0.06
    Act Density 0.027%

    No Known Activations