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

    Neuronpedia

    INDEX
    Explanations

    even

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isis
    -0.07
    ころ
    -0.07
     Orchard
    -0.06
    йте
    -0.06
    Warnings
    -0.06
    NewProp
    -0.06
    トリ
    -0.06
    igit
    -0.06
     програми
    -0.06
     lô
    -0.06
    POSITIVE LOGITS
     even
    0.09
     bagi
    0.07
     presenting
    0.07
     Even
    0.07
     Crawford
    0.06
     globals
    0.06
     ee
    0.06
    eren
    0.06
    .tail
    0.06
     declining
    0.06
    Act Density 0.024%

    No Known Activations