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

    Neuronpedia

    INDEX
    Explanations

    Question and answer context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dict
    -0.07
    Sync
    -0.07
    mittel
    -0.07
     decided
    -0.07
     setback
    -0.07
     зуп
    -0.06
     Charg
    -0.06
     likes
    -0.06
    Associate
    -0.06
    .Bottom
    -0.06
    POSITIVE LOGITS
     setPage
    0.07
    خل
    0.07
     Wow
    0.07
    視
    0.06
    (forms
    0.06
    /create
    0.06
    uyễn
    0.06
    xAE
    0.06
     HANDLE
    0.06
    ọng
    0.06
    Act Density 0.013%

    No Known Activations