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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .beta
    -0.07
    beck
    -0.07
     beams
    -0.06
     Tell
    -0.06
     Sequ
    -0.06
    _ph
    -0.06
     אז
    -0.06
    早上
    -0.06
    .background
    -0.06
    _make
    -0.06
    POSITIVE LOGITS
     declines
    0.07
     avoid
    0.07
     originated
    0.07
    油腻
    0.07
     Selected
    0.07
    枅
    0.06
    -gray
    0.06
     NotFoundException
    0.06
    arranty
    0.06
    玒
    0.06
    Act Density 0.031%

    No Known Activations