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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     who
    -0.07
    findOne
    -0.07
    하지만
    -0.07
    *((
    -0.07
    287
    -0.06
    who
    -0.06
     Howard
    -0.06
    Pedido
    -0.06
     Bentley
    -0.06
    کات
    -0.06
    POSITIVE LOGITS
    ány
    0.07
     anzeigen
    0.07
    otypical
    0.06
     kurum
    0.06
     sut
    0.06
     نو
    0.06
     tụ
    0.06
     cuer
    0.06
     Computational
    0.06
    ,J
    0.06
    Act Density 0.045%

    No Known Activations