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

    Neuronpedia

    INDEX
    Explanations

    stress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lte
    -0.07
     lup
    -0.07
    леч
    -0.06
     ル
    -0.06
     könnte
    -0.06
     corners
    -0.06
    proto
    -0.06
     clips
    -0.06
     下午
    -0.06
    こんな
    -0.06
    POSITIVE LOGITS
    BYTE
    0.07
    م
    0.06
    وسی
    0.06
    CHE
    0.06
     emphasized
    0.06
    기를
    0.06
     Note
    0.06
    KE
    0.06
     програми
    0.06
    EN
    0.06
    Act Density 0.014%

    No Known Activations