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

    Neuronpedia

    INDEX
    Explanations

    energy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pants
    -0.07
     assets
    -0.07
     Texas
    -0.07
     Args
    -0.07
    illow
    -0.07
     امور
    -0.06
     teens
    -0.06
    ペ
    -0.06
    Boxes
    -0.06
    .Cells
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ±
    0.07
    udicots
    0.07
     dra
    0.07
    慎
    0.07
     amb
    0.06
    .workflow
    0.06
     }}">
    0.06
     бур
    0.06
     onItemClick
    0.06
    Act Density 0.014%

    No Known Activations