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

    Neuronpedia

    INDEX
    Explanations

    say address parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atical
    -0.07
    ivia
    -0.07
    Slash
    -0.07
    Phoenix
    -0.07
    imized
    -0.07
     currentIndex
    -0.06
    вяз
    -0.06
    娃娃
    -0.06
    иков
    -0.06
    Senior
    -0.06
    POSITIVE LOGITS
     quyền
    0.08
    .run
    0.08
    *.
    0.07
     qry
    0.07
    .Name
    0.07
    _KHR
    0.07
    差异
    0.07
    ⌜
    0.07
     UNICODE
    0.06
     reserved
    0.06
    Act Density 0.003%

    No Known Activations