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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contour
    -0.07
    Convert
    -0.07
    )?
    -0.06
    Intel
    -0.06
     concerning
    -0.06
    -0.06
     Convert
    -0.06
     composite
    -0.06
    asper
    -0.06
     Embed
    -0.06
    POSITIVE LOGITS
     at
    0.10
     At
    0.07
    instructions
    0.07
    ヶ
    0.06
    ρισ
    0.06
    Д
    0.06
    ตำแหน
    0.06
    ění
    0.06
     ViewData
    0.06
    ์ได
    0.06
    Act Density 0.061%

    No Known Activations