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

    Neuronpedia

    INDEX
    Explanations

    contains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dx
    -0.06
     Laud
    -0.06
     defer
    -0.06
     distingu
    -0.06
    ^[
    -0.06
     paralyzed
    -0.06
    _subscribe
    -0.06
     ES
    -0.06
     restart
    -0.06
     zero
    -0.06
    POSITIVE LOGITS
    .WebServlet
    0.06
     فيه
    0.06
    .Vertex
    0.06
    ��
    0.06
     hrá
    0.06
    μοί
    0.06
    ifo
    0.06
     catast
    0.06
     workload
    0.06
     próximo
    0.06
    Act Density 0.025%

    No Known Activations